diff --git a/Makefile b/Makefile
index d22b9f2da984..89080d4d4970 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 10
-SUBLEVEL = 23
+SUBLEVEL = 24
 EXTRAVERSION =
 NAME = TOSSUG Baby Fish
 
diff --git a/arch/arm/boot/dts/armada-370-xp.dtsi b/arch/arm/boot/dts/armada-370-xp.dtsi
index 550eb772c30e..4d12d2347c15 100644
--- a/arch/arm/boot/dts/armada-370-xp.dtsi
+++ b/arch/arm/boot/dts/armada-370-xp.dtsi
@@ -51,7 +51,7 @@ mpic: interrupt-controller@20000 {
 
 			coherency-fabric@20200 {
 				compatible = "marvell,coherency-fabric";
-				reg = <0x20200 0xb0>, <0x21810 0x1c>;
+				reg = <0x20200 0xb0>, <0x21010 0x1c>;
 			};
 
 			serial@12000 {
diff --git a/arch/arm/boot/dts/armada-xp-mv78230.dtsi b/arch/arm/boot/dts/armada-xp-mv78230.dtsi
index f8eaa383e07f..f94cdbc579cb 100644
--- a/arch/arm/boot/dts/armada-xp-mv78230.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78230.dtsi
@@ -81,7 +81,7 @@ gpio1: gpio@18140 {
 			/*
 			 * MV78230 has 2 PCIe units Gen2.0: One unit can be
 			 * configured as x4 or quad x1 lanes. One unit is
-			 * x4/x1.
+			 * x1 only.
 			 */
 			pcie-controller {
 				compatible = "marvell,armada-xp-pcie";
@@ -94,10 +94,10 @@ pcie-controller {
 				bus-range = <0x00 0xff>;
 
 				ranges = <0x82000000 0 0x40000 0x40000 0 0x00002000   /* Port 0.0 registers */
-					0x82000000 0 0x42000 0x42000 0 0x00002000   /* Port 2.0 registers */
 					0x82000000 0 0x44000 0x44000 0 0x00002000   /* Port 0.1 registers */
 					0x82000000 0 0x48000 0x48000 0 0x00002000   /* Port 0.2 registers */
 					0x82000000 0 0x4c000 0x4c000 0 0x00002000   /* Port 0.3 registers */
+					0x82000000 0 0x80000 0x80000 0 0x00002000   /* Port 1.0 registers */
 					0x82000000 0 0xe0000000 0xe0000000 0 0x08000000   /* non-prefetchable memory */
 					0x81000000 0 0	  0xe8000000 0 0x00100000>; /* downstream I/O */
 
@@ -165,19 +165,19 @@ pcie@4,0 {
 					status = "disabled";
 				};
 
-				pcie@9,0 {
+				pcie@5,0 {
 					device_type = "pci";
-					assigned-addresses = <0x82000800 0 0x42000 0 0x2000>;
-					reg = <0x4800 0 0 0 0>;
+					assigned-addresses = <0x82000800 0 0x80000 0 0x2000>;
+					reg = <0x2800 0 0 0 0>;
 					#address-cells = <3>;
 					#size-cells = <2>;
 					#interrupt-cells = <1>;
 					ranges;
 					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 99>;
-					marvell,pcie-port = <2>;
+					interrupt-map = <0 0 0 0 &mpic 62>;
+					marvell,pcie-port = <1>;
 					marvell,pcie-lane = <0>;
-					clocks = <&gateclk 26>;
+					clocks = <&gateclk 9>;
 					status = "disabled";
 				};
 			};
diff --git a/arch/arm/boot/dts/armada-xp-mv78260.dtsi b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
index f4029f015aff..55cdd58c155f 100644
--- a/arch/arm/boot/dts/armada-xp-mv78260.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
@@ -101,7 +101,7 @@ ethernet@34000 {
 			/*
 			 * MV78260 has 3 PCIe units Gen2.0: Two units can be
 			 * configured as x4 or quad x1 lanes. One unit is
-			 * x4/x1.
+			 * x4 only.
 			 */
 			pcie-controller {
 				compatible = "marvell,armada-xp-pcie";
@@ -119,7 +119,9 @@ pcie-controller {
 					0x82000000 0 0x48000 0x48000 0 0x00002000   /* Port 0.2 registers */
 					0x82000000 0 0x4c000 0x4c000 0 0x00002000   /* Port 0.3 registers */
 					0x82000000 0 0x80000 0x80000 0 0x00002000   /* Port 1.0 registers */
-					0x82000000 0 0x82000 0x82000 0 0x00002000   /* Port 3.0 registers */
+					0x82000000 0 0x84000 0x84000 0 0x00002000   /* Port 1.1 registers */
+					0x82000000 0 0x88000 0x88000 0 0x00002000   /* Port 1.2 registers */
+					0x82000000 0 0x8c000 0x8c000 0 0x00002000   /* Port 1.3 registers */
 					0x82000000 0 0xe0000000 0xe0000000 0 0x08000000   /* non-prefetchable memory */
 					0x81000000 0 0	  0xe8000000 0 0x00100000>; /* downstream I/O */
 
@@ -187,6 +189,70 @@ pcie@4,0 {
 					status = "disabled";
 				};
 
+				pcie@5,0 {
+					device_type = "pci";
+					assigned-addresses = <0x82000800 0 0x80000 0 0x2000>;
+					reg = <0x2800 0 0 0 0>;
+					#address-cells = <3>;
+					#size-cells = <2>;
+					#interrupt-cells = <1>;
+					ranges;
+					interrupt-map-mask = <0 0 0 0>;
+					interrupt-map = <0 0 0 0 &mpic 62>;
+					marvell,pcie-port = <1>;
+					marvell,pcie-lane = <0>;
+					clocks = <&gateclk 9>;
+					status = "disabled";
+				};
+
+				pcie@6,0 {
+					device_type = "pci";
+					assigned-addresses = <0x82000800 0 0x84000 0 0x2000>;
+					reg = <0x3000 0 0 0 0>;
+					#address-cells = <3>;
+					#size-cells = <2>;
+					#interrupt-cells = <1>;
+					ranges;
+					interrupt-map-mask = <0 0 0 0>;
+					interrupt-map = <0 0 0 0 &mpic 63>;
+					marvell,pcie-port = <1>;
+					marvell,pcie-lane = <1>;
+					clocks = <&gateclk 10>;
+					status = "disabled";
+				};
+
+				pcie@7,0 {
+					device_type = "pci";
+					assigned-addresses = <0x82000800 0 0x88000 0 0x2000>;
+					reg = <0x3800 0 0 0 0>;
+					#address-cells = <3>;
+					#size-cells = <2>;
+					#interrupt-cells = <1>;
+					ranges;
+					interrupt-map-mask = <0 0 0 0>;
+					interrupt-map = <0 0 0 0 &mpic 64>;
+					marvell,pcie-port = <1>;
+					marvell,pcie-lane = <2>;
+					clocks = <&gateclk 11>;
+					status = "disabled";
+				};
+
+				pcie@8,0 {
+					device_type = "pci";
+					assigned-addresses = <0x82000800 0 0x8c000 0 0x2000>;
+					reg = <0x4000 0 0 0 0>;
+					#address-cells = <3>;
+					#size-cells = <2>;
+					#interrupt-cells = <1>;
+					ranges;
+					interrupt-map-mask = <0 0 0 0>;
+					interrupt-map = <0 0 0 0 &mpic 65>;
+					marvell,pcie-port = <1>;
+					marvell,pcie-lane = <3>;
+					clocks = <&gateclk 12>;
+					status = "disabled";
+				};
+
 				pcie@9,0 {
 					device_type = "pci";
 					assigned-addresses = <0x82000800 0 0x42000 0 0x2000>;
@@ -202,22 +268,6 @@ pcie@9,0 {
 					clocks = <&gateclk 26>;
 					status = "disabled";
 				};
-
-				pcie@10,0 {
-					device_type = "pci";
-					assigned-addresses = <0x82000800 0 0x82000 0 0x2000>;
-					reg = <0x5000 0 0 0 0>;
-					#address-cells = <3>;
-					#size-cells = <2>;
-					#interrupt-cells = <1>;
-					ranges;
-					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 103>;
-					marvell,pcie-port = <3>;
-					marvell,pcie-lane = <0>;
-					clocks = <&gateclk 27>;
-					status = "disabled";
-				};
 			};
 		};
 	};
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 3e94af33aa6f..97b61a58695a 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -437,4 +437,50 @@ static inline void __sync_cache_range_r(volatile void *p, size_t size)
 #define sync_cache_w(ptr) __sync_cache_range_w(ptr, sizeof *(ptr))
 #define sync_cache_r(ptr) __sync_cache_range_r(ptr, sizeof *(ptr))
 
+/*
+ * Disabling cache access for one CPU in an ARMv7 SMP system is tricky.
+ * To do so we must:
+ *
+ * - Clear the SCTLR.C bit to prevent further cache allocations
+ * - Flush the desired level of cache
+ * - Clear the ACTLR "SMP" bit to disable local coherency
+ *
+ * ... and so without any intervening memory access in between those steps,
+ * not even to the stack.
+ *
+ * WARNING -- After this has been called:
+ *
+ * - No ldrex/strex (and similar) instructions must be used.
+ * - The CPU is obviously no longer coherent with the other CPUs.
+ * - This is unlikely to work as expected if Linux is running non-secure.
+ *
+ * Note:
+ *
+ * - This is known to apply to several ARMv7 processor implementations,
+ *   however some exceptions may exist.  Caveat emptor.
+ *
+ * - The clobber list is dictated by the call to v7_flush_dcache_*.
+ *   fp is preserved to the stack explicitly prior disabling the cache
+ *   since adding it to the clobber list is incompatible with having
+ *   CONFIG_FRAME_POINTER=y.  ip is saved as well if ever r12-clobbering
+ *   trampoline are inserted by the linker and to keep sp 64-bit aligned.
+ */
+#define v7_exit_coherency_flush(level) \
+	asm volatile( \
+	"stmfd	sp!, {fp, ip} \n\t" \
+	"mrc	p15, 0, r0, c1, c0, 0	@ get SCTLR \n\t" \
+	"bic	r0, r0, #"__stringify(CR_C)" \n\t" \
+	"mcr	p15, 0, r0, c1, c0, 0	@ set SCTLR \n\t" \
+	"isb	\n\t" \
+	"bl	v7_flush_dcache_"__stringify(level)" \n\t" \
+	"clrex	\n\t" \
+	"mrc	p15, 0, r0, c1, c0, 1	@ get ACTLR \n\t" \
+	"bic	r0, r0, #(1 << 6)	@ disable local coherency \n\t" \
+	"mcr	p15, 0, r0, c1, c0, 1	@ set ACTLR \n\t" \
+	"isb	\n\t" \
+	"dsb	\n\t" \
+	"ldmfd	sp!, {fp, ip}" \
+	: : : "r0","r1","r2","r3","r4","r5","r6","r7", \
+	      "r9","r10","lr","memory" )
+
 #endif
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 9bcd262a9008..5aac06fcc97e 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -58,7 +58,7 @@ extern void __pgd_error(const char *file, int line, pgd_t);
  * mapping to be mapped at.  This is particularly important for
  * non-high vector CPUs.
  */
-#define FIRST_USER_ADDRESS	PAGE_SIZE
+#define FIRST_USER_ADDRESS	(PAGE_SIZE * 2)
 
 /*
  * Use TASK_SIZE as the ceiling argument for free_pgtables() and
diff --git a/arch/arm/mach-at91/sama5d3.c b/arch/arm/mach-at91/sama5d3.c
index 3ea86428ee09..a28873fe3049 100644
--- a/arch/arm/mach-at91/sama5d3.c
+++ b/arch/arm/mach-at91/sama5d3.c
@@ -95,19 +95,19 @@ static struct clk twi0_clk = {
 	.name		= "twi0_clk",
 	.pid		= SAMA5D3_ID_TWI0,
 	.type		= CLK_TYPE_PERIPHERAL,
-	.div		= AT91_PMC_PCR_DIV2,
+	.div		= AT91_PMC_PCR_DIV8,
 };
 static struct clk twi1_clk = {
 	.name		= "twi1_clk",
 	.pid		= SAMA5D3_ID_TWI1,
 	.type		= CLK_TYPE_PERIPHERAL,
-	.div		= AT91_PMC_PCR_DIV2,
+	.div		= AT91_PMC_PCR_DIV8,
 };
 static struct clk twi2_clk = {
 	.name		= "twi2_clk",
 	.pid		= SAMA5D3_ID_TWI2,
 	.type		= CLK_TYPE_PERIPHERAL,
-	.div		= AT91_PMC_PCR_DIV2,
+	.div		= AT91_PMC_PCR_DIV8,
 };
 static struct clk mmc0_clk = {
 	.name		= "mci0_clk",
diff --git a/arch/arm/mach-footbridge/common.c b/arch/arm/mach-footbridge/common.c
index a42b369bc439..95d0b6e6438b 100644
--- a/arch/arm/mach-footbridge/common.c
+++ b/arch/arm/mach-footbridge/common.c
@@ -15,6 +15,7 @@
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/spinlock.h>
+#include <video/vga.h>
 
 #include <asm/pgtable.h>
 #include <asm/page.h>
@@ -196,6 +197,8 @@ void __init footbridge_map_io(void)
 		iotable_init(ebsa285_host_io_desc, ARRAY_SIZE(ebsa285_host_io_desc));
 		pci_map_io_early(__phys_to_pfn(DC21285_PCI_IO));
 	}
+
+	vga_base = PCIMEM_BASE;
 }
 
 void footbridge_restart(char mode, const char *cmd)
diff --git a/arch/arm/mach-footbridge/dc21285.c b/arch/arm/mach-footbridge/dc21285.c
index 3490a24f969e..7c2fdae9a38b 100644
--- a/arch/arm/mach-footbridge/dc21285.c
+++ b/arch/arm/mach-footbridge/dc21285.c
@@ -18,7 +18,6 @@
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/spinlock.h>
-#include <video/vga.h>
 
 #include <asm/irq.h>
 #include <asm/mach/pci.h>
@@ -291,7 +290,6 @@ void __init dc21285_preinit(void)
 	int cfn_mode;
 
 	pcibios_min_mem = 0x81000000;
-	vga_base = PCIMEM_BASE;
 
 	mem_size = (unsigned int)high_memory - PAGE_OFFSET;
 	for (mem_mask = 0x00100000; mem_mask < 0x10000000; mem_mask <<= 1)
diff --git a/arch/arm/mach-footbridge/ebsa285.c b/arch/arm/mach-footbridge/ebsa285.c
index b08243500e2e..1a7235fb52ac 100644
--- a/arch/arm/mach-footbridge/ebsa285.c
+++ b/arch/arm/mach-footbridge/ebsa285.c
@@ -30,21 +30,24 @@ static const struct {
 	const char *name;
 	const char *trigger;
 } ebsa285_leds[] = {
-	{ "ebsa285:amber", "heartbeat", },
-	{ "ebsa285:green", "cpu0", },
+	{ "ebsa285:amber", "cpu0", },
+	{ "ebsa285:green", "heartbeat", },
 	{ "ebsa285:red",},
 };
 
+static unsigned char hw_led_state;
+
 static void ebsa285_led_set(struct led_classdev *cdev,
 		enum led_brightness b)
 {
 	struct ebsa285_led *led = container_of(cdev,
 			struct ebsa285_led, cdev);
 
-	if (b != LED_OFF)
-		*XBUS_LEDS |= led->mask;
+	if (b == LED_OFF)
+		hw_led_state |= led->mask;
 	else
-		*XBUS_LEDS &= ~led->mask;
+		hw_led_state &= ~led->mask;
+	*XBUS_LEDS = hw_led_state;
 }
 
 static enum led_brightness ebsa285_led_get(struct led_classdev *cdev)
@@ -52,18 +55,19 @@ static enum led_brightness ebsa285_led_get(struct led_classdev *cdev)
 	struct ebsa285_led *led = container_of(cdev,
 			struct ebsa285_led, cdev);
 
-	return (*XBUS_LEDS & led->mask) ? LED_FULL : LED_OFF;
+	return hw_led_state & led->mask ? LED_OFF : LED_FULL;
 }
 
 static int __init ebsa285_leds_init(void)
 {
 	int i;
 
-	if (machine_is_ebsa285())
+	if (!machine_is_ebsa285())
 		return -ENODEV;
 
-	/* 3 LEDS All ON */
-	*XBUS_LEDS |= XBUS_LED_AMBER | XBUS_LED_GREEN | XBUS_LED_RED;
+	/* 3 LEDS all off */
+	hw_led_state = XBUS_LED_AMBER | XBUS_LED_GREEN | XBUS_LED_RED;
+	*XBUS_LEDS = hw_led_state;
 
 	for (i = 0; i < ARRAY_SIZE(ebsa285_leds); i++) {
 		struct ebsa285_led *led;
diff --git a/arch/arm/mach-vexpress/dcscb.c b/arch/arm/mach-vexpress/dcscb.c
index 948aec0890f5..b35700f8e01f 100644
--- a/arch/arm/mach-vexpress/dcscb.c
+++ b/arch/arm/mach-vexpress/dcscb.c
@@ -134,17 +134,8 @@ static void dcscb_power_down(void)
 	if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) {
 		arch_spin_unlock(&dcscb_lock);
 
-		/*
-		 * Flush all cache levels for this cluster.
-		 *
-		 * A15/A7 can hit in the cache with SCTLR.C=0, so we don't need
-		 * a preliminary flush here for those CPUs.  At least, that's
-		 * the theory -- without the extra flush, Linux explodes on
-		 * RTSM (to be investigated).
-		 */
-		flush_cache_all();
-		set_cr(get_cr() & ~CR_C);
-		flush_cache_all();
+		/* Flush all cache levels for this cluster. */
+		v7_exit_coherency_flush(all);
 
 		/*
 		 * This is a harmless no-op.  On platforms with a real
@@ -153,9 +144,6 @@ static void dcscb_power_down(void)
 		 */
 		outer_flush_all();
 
-		/* Disable local coherency by clearing the ACTLR "SMP" bit: */
-		set_auxcr(get_auxcr() & ~(1 << 6));
-
 		/*
 		 * Disable cluster-level coherency by masking
 		 * incoming snoops and DVM messages:
@@ -166,20 +154,8 @@ static void dcscb_power_down(void)
 	} else {
 		arch_spin_unlock(&dcscb_lock);
 
-		/*
-		 * Flush the local CPU cache.
-		 *
-		 * A15/A7 can hit in the cache with SCTLR.C=0, so we don't need
-		 * a preliminary flush here for those CPUs.  At least, that's
-		 * the theory -- without the extra flush, Linux explodes on
-		 * RTSM (to be investigated).
-		 */
-		flush_cache_louis();
-		set_cr(get_cr() & ~CR_C);
-		flush_cache_louis();
-
-		/* Disable local coherency by clearing the ACTLR "SMP" bit: */
-		set_auxcr(get_auxcr() & ~(1 << 6));
+		/* Disable and flush the local CPU cache. */
+		v7_exit_coherency_flush(louis);
 	}
 
 	__mcpm_cpu_down(cpu, cluster);
diff --git a/arch/arm/mach-vexpress/tc2_pm.c b/arch/arm/mach-vexpress/tc2_pm.c
index 2b519eee84d8..9fc264a3bade 100644
--- a/arch/arm/mach-vexpress/tc2_pm.c
+++ b/arch/arm/mach-vexpress/tc2_pm.c
@@ -135,21 +135,22 @@ static void tc2_pm_down(u64 residency)
 	if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) {
 		arch_spin_unlock(&tc2_pm_lock);
 
-		set_cr(get_cr() & ~CR_C);
-		flush_cache_all();
-		asm volatile ("clrex");
-		set_auxcr(get_auxcr() & ~(1 << 6));
+		if (read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A15) {
+			/*
+			 * On the Cortex-A15 we need to disable
+			 * L2 prefetching before flushing the cache.
+			 */
+			asm volatile(
+			"mcr	p15, 1, %0, c15, c0, 3 \n\t"
+			"isb	\n\t"
+			"dsb	"
+			: : "r" (0x400) );
+		}
+
+		v7_exit_coherency_flush(all);
 
 		cci_disable_port_by_cpu(mpidr);
 
-		/*
-		 * Ensure that both C & I bits are disabled in the SCTLR
-		 * before disabling ACE snoops. This ensures that no
-		 * coherency traffic will originate from this cpu after
-		 * ACE snoops are turned off.
-		 */
-		cpu_proc_fin();
-
 		__mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN);
 	} else {
 		/*
@@ -162,10 +163,7 @@ static void tc2_pm_down(u64 residency)
 
 		arch_spin_unlock(&tc2_pm_lock);
 
-		set_cr(get_cr() & ~CR_C);
-		flush_cache_louis();
-		asm volatile ("clrex");
-		set_auxcr(get_auxcr() & ~(1 << 6));
+		v7_exit_coherency_flush(louis);
 	}
 
 	__mcpm_cpu_down(cpu, cluster);
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index 10062ceadd1c..f0ef2f7d4ad7 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -146,7 +146,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 
 	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
 	info.length = len;
-	info.low_limit = PAGE_SIZE;
+	info.low_limit = FIRST_USER_ADDRESS;
 	info.high_limit = mm->mmap_base;
 	info.align_mask = do_align ? (PAGE_MASK & (SHMLBA - 1)) : 0;
 	info.align_offset = pgoff << PAGE_SHIFT;
diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index 0acb089d0f70..1046b373d1ae 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -87,7 +87,8 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 		init_pud = pud_offset(init_pgd, 0);
 		init_pmd = pmd_offset(init_pud, 0);
 		init_pte = pte_offset_map(init_pmd, 0);
-		set_pte_ext(new_pte, *init_pte, 0);
+		set_pte_ext(new_pte + 0, init_pte[0], 0);
+		set_pte_ext(new_pte + 1, init_pte[1], 0);
 		pte_unmap(init_pte);
 		pte_unmap(new_pte);
 	}
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 56b3f6d447ae..a95dc907a139 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -144,12 +144,139 @@ config SMP
 
 	  If you don't know what to do here, say N.
 
+config ARM_CPU_TOPOLOGY
+	bool "Support CPU topology definition"
+	depends on SMP
+	default y
+	help
+	  Support CPU topology definition, based on configuration
+	  provided by the firmware.
+
+config SCHED_MC
+	bool "Multi-core scheduler support"
+	depends on ARM_CPU_TOPOLOGY
+	help
+	  Multi-core scheduler support improves the CPU scheduler's decision
+	  making when dealing with multi-core CPU chips at a cost of slightly
+	  increased overhead in some places. If unsure say N here.
+
+config SCHED_SMT
+	bool "SMT scheduler support"
+	depends on ARM_CPU_TOPOLOGY
+	help
+	  Improves the CPU scheduler's decision making when dealing with
+	  MultiThreading at a cost of slightly increased overhead in some
+	  places. If unsure say N here.
+
+config DISABLE_CPU_SCHED_DOMAIN_BALANCE
+	bool "(EXPERIMENTAL) Disable CPU level scheduler load-balancing"
+	help
+	  Disables scheduler load-balancing at CPU sched domain level.
+
+config SCHED_HMP
+	bool "(EXPERIMENTAL) Heterogenous multiprocessor scheduling"
+	depends on DISABLE_CPU_SCHED_DOMAIN_BALANCE && SCHED_MC && FAIR_GROUP_SCHED && !SCHED_AUTOGROUP
+	help
+	  Experimental scheduler optimizations for heterogeneous platforms.
+	  Attempts to introspectively select task affinity to optimize power
+	  and performance. Basic support for multiple (>2) cpu types is in place,
+	  but it has only been tested with two types of cpus.
+	  There is currently no support for migration of task groups, hence
+	  !SCHED_AUTOGROUP. Furthermore, normal load-balancing must be disabled
+	  between cpus of different type (DISABLE_CPU_SCHED_DOMAIN_BALANCE).
+
+config SCHED_HMP_PRIO_FILTER
+	bool "(EXPERIMENTAL) Filter HMP migrations by task priority"
+	depends on SCHED_HMP
+	help
+	  Enables task priority based HMP migration filter. Any task with
+	  a NICE value above the threshold will always be on low-power cpus
+	  with less compute capacity.
+
+config SCHED_HMP_PRIO_FILTER_VAL
+	int "NICE priority threshold"
+	default 5
+	depends on SCHED_HMP_PRIO_FILTER
+
+config HMP_FAST_CPU_MASK
+	string "HMP scheduler fast CPU mask"
+	depends on SCHED_HMP
+	help
+          Leave empty to use device tree information.
+	  Specify the cpuids of the fast CPUs in the system as a list string,
+	  e.g. cpuid 0+1 should be specified as 0-1.
+
+config HMP_SLOW_CPU_MASK
+	string "HMP scheduler slow CPU mask"
+	depends on SCHED_HMP
+	help
+	  Leave empty to use device tree information.
+	  Specify the cpuids of the slow CPUs in the system as a list string,
+	  e.g. cpuid 0+1 should be specified as 0-1.
+
+config HMP_VARIABLE_SCALE
+	bool "Allows changing the load tracking scale through sysfs"
+	depends on SCHED_HMP
+	help
+	  When turned on, this option exports the thresholds and load average
+	  period value for the load tracking patches through sysfs.
+	  The values can be modified to change the rate of load accumulation
+	  and the thresholds used for HMP migration.
+	  The load_avg_period_ms is the time in ms to reach a load average of
+	  0.5 for an idle task of 0 load average ratio that start a busy loop.
+	  The up_threshold and down_threshold is the value to go to a faster
+	  CPU or to go back to a slower cpu.
+	  The {up,down}_threshold are devided by 1024 before being compared
+	  to the load average.
+	  For examples, with load_avg_period_ms = 128 and up_threshold = 512,
+	  a running task with a load of 0 will be migrated to a bigger CPU after
+	  128ms, because after 128ms its load_avg_ratio is 0.5 and the real
+	  up_threshold is 0.5.
+	  This patch has the same behavior as changing the Y of the load
+	  average computation to
+	        (1002/1024)^(LOAD_AVG_PERIOD/load_avg_period_ms)
+	  but it remove intermadiate overflows in computation.
+
+config HMP_FREQUENCY_INVARIANT_SCALE
+	bool "(EXPERIMENTAL) Frequency-Invariant Tracked Load for HMP"
+	depends on HMP_VARIABLE_SCALE && CPU_FREQ
+	help
+	  Scales the current load contribution in line with the frequency
+	  of the CPU that the task was executed on.
+	  In this version, we use a simple linear scale derived from the
+	  maximum frequency reported by CPUFreq.
+	  Restricting tracked load to be scaled by the CPU's frequency
+	  represents the consumption of possible compute capacity
+	  (rather than consumption of actual instantaneous capacity as
+	  normal) and allows the HMP migration's simple threshold
+	  migration strategy to interact more predictably with CPUFreq's
+	  asynchronous compute capacity changes.
+
+config SCHED_HMP_LITTLE_PACKING
+	bool "Small task packing for HMP"
+	depends on SCHED_HMP
+	default n
+	help
+	  Allows the HMP Scheduler to pack small tasks into CPUs in the
+	  smallest HMP domain.
+	  Controlled by two sysfs files in sys/kernel/hmp.
+	  packing_enable: 1 to enable, 0 to disable packing. Default 1.
+	  packing_limit: runqueue load ratio where a RQ is considered
+	    to be full. Default is NICE_0_LOAD * 9/8.
+
 config NR_CPUS
 	int "Maximum number of CPUs (2-32)"
 	range 2 32
 	depends on SMP
 	default "4"
 
+config HOTPLUG_CPU
+	bool "Support for hot-pluggable CPUs"
+	depends on SMP
+	help
+	  Say Y here to experiment with turning CPUs off and on.  CPUs
+	  can be controlled through /sys/devices/system/cpu.
+
 source kernel/Kconfig.preempt
 
 config HZ
@@ -229,6 +356,14 @@ config SYSVIPC_COMPAT
 
 endmenu
 
+menu "Power management options"
+
+source "kernel/power/Kconfig"
+
+source "drivers/cpufreq/Kconfig"
+
+endmenu
+
 source "net/Kconfig"
 
 source "drivers/Kconfig"
diff --git a/arch/arm64/boot/dts/Makefile b/arch/arm64/boot/dts/Makefile
index 68457e9e0975..24be4296c14c 100644
--- a/arch/arm64/boot/dts/Makefile
+++ b/arch/arm64/boot/dts/Makefile
@@ -1,4 +1,5 @@
-dtb-$(CONFIG_ARCH_VEXPRESS) += rtsm_ve-aemv8a.dtb foundation-v8.dtb
+dtb-$(CONFIG_ARCH_VEXPRESS) += rtsm_ve-aemv8a.dtb foundation-v8.dtb \
+				fvp-base-gicv2-psci.dtb
 
 targets += dtbs
 targets += $(dtb-y)
diff --git a/arch/arm64/boot/dts/fvp-base-gicv2-psci.dts b/arch/arm64/boot/dts/fvp-base-gicv2-psci.dts
new file mode 100644
index 000000000000..79ddd464c7d0
--- /dev/null
+++ b/arch/arm64/boot/dts/fvp-base-gicv2-psci.dts
@@ -0,0 +1,287 @@
+/*
+ * Copyright (c) 2013, ARM Limited. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * Redistributions of source code must retain the above copyright notice, this
+ * list of conditions and the following disclaimer.
+ *
+ * Redistributions in binary form must reproduce the above copyright notice,
+ * this list of conditions and the following disclaimer in the documentation
+ * and/or other materials provided with the distribution.
+ *
+ * Neither the name of ARM nor the names of its contributors may be used
+ * to endorse or promote products derived from this software without specific
+ * prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/dts-v1/;
+
+/memreserve/ 0x80000000 0x00010000;
+
+/ {
+};
+
+/ {
+	model = "FVP Base";
+	compatible = "arm,vfp-base", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	chosen { };
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+	};
+
+	psci {
+		compatible = "arm,psci";
+		method = "smc";
+		cpu_suspend = <0xc4000001>;
+		cpu_off = <0x84000002>;
+		cpu_on = <0xc4000003>;
+	};
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		big0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a57", "arm,armv8";
+			reg = <0x0 0x0>;
+			enable-method = "psci";
+			clock-frequency = <1000000>;
+		};
+		big1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a57", "arm,armv8";
+			reg = <0x0 0x1>;
+			enable-method = "psci";
+			clock-frequency = <1000000>;
+		};
+		big2: cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a57", "arm,armv8";
+			reg = <0x0 0x2>;
+			enable-method = "psci";
+			clock-frequency = <1000000>;
+		};
+		big3: cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a57", "arm,armv8";
+			reg = <0x0 0x3>;
+			enable-method = "psci";
+			clock-frequency = <1000000>;
+		};
+		little0: cpu@100 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x100>;
+			enable-method = "psci";
+			clock-frequency = <1000000>;
+		};
+		little1: cpu@101 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x101>;
+			enable-method = "psci";
+			clock-frequency = <1000000>;
+		};
+		little2: cpu@102 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x102>;
+			enable-method = "psci";
+			clock-frequency = <1000000>;
+		};
+		little3: cpu@103 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x103>;
+			enable-method = "psci";
+			clock-frequency = <1000000>;
+		};
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&big0>;
+				};
+				core1 {
+					cpu = <&big1>;
+				};
+				core2 {
+					cpu = <&big2>;
+				};
+				core3 {
+					cpu = <&big3>;
+				};
+			};
+			cluster1 {
+				core0 {
+					cpu = <&little0>;
+				};
+				core1 {
+					cpu = <&little1>;
+				};
+				core2 {
+					cpu = <&little2>;
+				};
+				core3 {
+					cpu = <&little3>;
+				};
+			};
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x00000000 0x80000000 0 0x80000000>,
+		      <0x00000008 0x80000000 0 0x80000000>;
+	};
+
+	gic: interrupt-controller@2f000000 {
+		compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0x0 0x2f000000 0 0x10000>,
+		      <0x0 0x2c000000 0 0x2000>,
+		      <0x0 0x2c010000 0 0x2000>,
+		      <0x0 0x2c02F000 0 0x2000>;
+		interrupts = <1 9 0xf04>;
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts = <1 13 0xff01>,
+			     <1 14 0xff01>,
+			     <1 11 0xff01>,
+			     <1 10 0xff01>;
+		clock-frequency = <100000000>;
+	};
+
+	timer@2a810000 {
+			compatible = "arm,armv7-timer-mem";
+			reg = <0x0 0x2a810000 0x0 0x10000>;
+			clock-frequency = <100000000>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+			frame@2a820000 {
+				frame-number = <0>;
+				interrupts = <0 25 4>;
+				reg = <0x0 0x2a820000 0x0 0x10000>;
+			};
+	};
+
+	pmu {
+		compatible = "arm,armv8-pmuv3";
+		interrupts = <0 60 4>,
+			     <0 61 4>,
+			     <0 62 4>,
+			     <0 63 4>;
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x08000000 0x04000000>,
+			 <1 0 0 0x14000000 0x04000000>,
+			 <2 0 0 0x18000000 0x04000000>,
+			 <3 0 0 0x1c000000 0x04000000>,
+			 <4 0 0 0x0c000000 0x04000000>,
+			 <5 0 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic 0  0 4>,
+				<0 0  1 &gic 0  1 4>,
+				<0 0  2 &gic 0  2 4>,
+				<0 0  3 &gic 0  3 4>,
+				<0 0  4 &gic 0  4 4>,
+				<0 0  5 &gic 0  5 4>,
+				<0 0  6 &gic 0  6 4>,
+				<0 0  7 &gic 0  7 4>,
+				<0 0  8 &gic 0  8 4>,
+				<0 0  9 &gic 0  9 4>,
+				<0 0 10 &gic 0 10 4>,
+				<0 0 11 &gic 0 11 4>,
+				<0 0 12 &gic 0 12 4>,
+				<0 0 13 &gic 0 13 4>,
+				<0 0 14 &gic 0 14 4>,
+				<0 0 15 &gic 0 15 4>,
+				<0 0 16 &gic 0 16 4>,
+				<0 0 17 &gic 0 17 4>,
+				<0 0 18 &gic 0 18 4>,
+				<0 0 19 &gic 0 19 4>,
+				<0 0 20 &gic 0 20 4>,
+				<0 0 21 &gic 0 21 4>,
+				<0 0 22 &gic 0 22 4>,
+				<0 0 23 &gic 0 23 4>,
+				<0 0 24 &gic 0 24 4>,
+				<0 0 25 &gic 0 25 4>,
+				<0 0 26 &gic 0 26 4>,
+				<0 0 27 &gic 0 27 4>,
+				<0 0 28 &gic 0 28 4>,
+				<0 0 29 &gic 0 29 4>,
+				<0 0 30 &gic 0 30 4>,
+				<0 0 31 &gic 0 31 4>,
+				<0 0 32 &gic 0 32 4>,
+				<0 0 33 &gic 0 33 4>,
+				<0 0 34 &gic 0 34 4>,
+				<0 0 35 &gic 0 35 4>,
+				<0 0 36 &gic 0 36 4>,
+				<0 0 37 &gic 0 37 4>,
+				<0 0 38 &gic 0 38 4>,
+				<0 0 39 &gic 0 39 4>,
+				<0 0 40 &gic 0 40 4>,
+				<0 0 41 &gic 0 41 4>,
+				<0 0 42 &gic 0 42 4>;
+
+		/include/ "rtsm_ve-motherboard.dtsi"
+	};
+
+	panels {
+		panel@0 {
+			compatible	= "panel";
+			mode		= "XVGA";
+			refresh		= <60>;
+			xres		= <1024>;
+			yres		= <768>;
+			pixclock	= <15748>;
+			left_margin	= <152>;
+			right_margin	= <48>;
+			upper_margin	= <23>;
+			lower_margin	= <3>;
+			hsync_len	= <104>;
+			vsync_len	= <4>;
+			sync		= <0>;
+			vmode		= "FB_VMODE_NONINTERLACED";
+			tim2		= "TIM2_BCD", "TIM2_IPC";
+			cntl		= "CNTL_LCDTFT", "CNTL_BGR", "CNTL_LCDVCOMP(1)";
+			caps		= "CLCD_CAP_5551", "CLCD_CAP_565", "CLCD_CAP_888";
+			bpp		= <16>;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/rtsm_ve-motherboard.dtsi b/arch/arm64/boot/dts/rtsm_ve-motherboard.dtsi
index b45e5f39f577..2f2ecd217363 100644
--- a/arch/arm64/boot/dts/rtsm_ve-motherboard.dtsi
+++ b/arch/arm64/boot/dts/rtsm_ve-motherboard.dtsi
@@ -183,6 +183,12 @@ clcd@1f0000 {
 				clocks = <&v2m_oscclk1>, <&v2m_clk24mhz>;
 				clock-names = "clcdclk", "apb_pclk";
 			};
+
+			virtio_block@0130000 {
+				compatible = "virtio,mmio";
+				reg = <0x130000 0x200>;
+				interrupts = <42>;
+			};
 		};
 
 		v2m_fixed_3v3: fixedregulator@0 {
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index 8a8ce0e73a38..68d7c932a9c3 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -158,17 +158,23 @@ static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
 	return ret;
 }
 
-#define cmpxchg(ptr,o,n)						\
-	((__typeof__(*(ptr)))__cmpxchg_mb((ptr),			\
-					  (unsigned long)(o),		\
-					  (unsigned long)(n),		\
-					  sizeof(*(ptr))))
+#define cmpxchg(ptr, o, n) \
+({ \
+	__typeof__(*(ptr)) __ret; \
+	__ret = (__typeof__(*(ptr))) \
+	__cmpxchg_mb((ptr), (unsigned long)(o), (unsigned long)(n), \
+		sizeof(*(ptr))); \
+	__ret; \
+})
 
-#define cmpxchg_local(ptr,o,n)						\
-	((__typeof__(*(ptr)))__cmpxchg((ptr),				\
-				       (unsigned long)(o),		\
-				       (unsigned long)(n),		\
-				       sizeof(*(ptr))))
+#define cmpxchg_local(ptr, o, n) \
+({ \
+	__typeof__(*(ptr)) __ret; \
+	__ret = (__typeof__(*(ptr))) \
+	__cmpxchg((ptr), (unsigned long)(o), \
+		(unsigned long)(n), sizeof(*(ptr))); \
+	__ret; \
+})
 
 #define cmpxchg64(ptr,o,n)		cmpxchg((ptr),(o),(n))
 #define cmpxchg64_local(ptr,o,n)	cmpxchg_local((ptr),(o),(n))
diff --git a/arch/arm64/include/asm/cpu_ops.h b/arch/arm64/include/asm/cpu_ops.h
new file mode 100644
index 000000000000..c4cdb5e5b73d
--- /dev/null
+++ b/arch/arm64/include/asm/cpu_ops.h
@@ -0,0 +1,59 @@
+/*
+ * Copyright (C) 2013 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_CPU_OPS_H
+#define __ASM_CPU_OPS_H
+
+#include <linux/init.h>
+#include <linux/threads.h>
+
+struct device_node;
+
+/**
+ * struct cpu_operations - Callback operations for hotplugging CPUs.
+ *
+ * @name:	Name of the property as appears in a devicetree cpu node's
+ *		enable-method property.
+ * @cpu_init:	Reads any data necessary for a specific enable-method from the
+ *		devicetree, for a given cpu node and proposed logical id.
+ * @cpu_prepare: Early one-time preparation step for a cpu. If there is a
+ *		mechanism for doing so, tests whether it is possible to boot
+ *		the given CPU.
+ * @cpu_boot:	Boots a cpu into the kernel.
+ * @cpu_postboot: Optionally, perform any post-boot cleanup or necesary
+ *		synchronisation. Called from the cpu being booted.
+ * @cpu_disable: Prepares a cpu to die. May fail for some mechanism-specific
+ * 		reason, which will cause the hot unplug to be aborted. Called
+ * 		from the cpu to be killed.
+ * @cpu_die:	Makes a cpu leave the kernel. Must not fail. Called from the
+ *		cpu being killed.
+ */
+struct cpu_operations {
+	const char	*name;
+	int		(*cpu_init)(struct device_node *, unsigned int);
+	int		(*cpu_prepare)(unsigned int);
+	int		(*cpu_boot)(unsigned int);
+	void		(*cpu_postboot)(void);
+#ifdef CONFIG_HOTPLUG_CPU
+	int		(*cpu_disable)(unsigned int cpu);
+	void		(*cpu_die)(unsigned int cpu);
+#endif
+};
+
+extern const struct cpu_operations *cpu_ops[NR_CPUS];
+extern int __init cpu_read_ops(struct device_node *dn, int cpu);
+extern void __init cpu_read_bootcpu_ops(void);
+
+#endif /* ifndef __ASM_CPU_OPS_H */
diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h
index 0332fc077f6e..e1f7ecdde11f 100644
--- a/arch/arm64/include/asm/irq.h
+++ b/arch/arm64/include/asm/irq.h
@@ -4,6 +4,7 @@
 #include <asm-generic/irq.h>
 
 extern void (*handle_arch_irq)(struct pt_regs *);
+extern void migrate_irqs(void);
 extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
 
 #endif
diff --git a/arch/arm64/include/asm/psci.h b/arch/arm64/include/asm/psci.h
index 0604237ecd99..e5312ea0ec1a 100644
--- a/arch/arm64/include/asm/psci.h
+++ b/arch/arm64/include/asm/psci.h
@@ -14,25 +14,6 @@
 #ifndef __ASM_PSCI_H
 #define __ASM_PSCI_H
 
-#define PSCI_POWER_STATE_TYPE_STANDBY		0
-#define PSCI_POWER_STATE_TYPE_POWER_DOWN	1
-
-struct psci_power_state {
-	u16	id;
-	u8	type;
-	u8	affinity_level;
-};
-
-struct psci_operations {
-	int (*cpu_suspend)(struct psci_power_state state,
-			   unsigned long entry_point);
-	int (*cpu_off)(struct psci_power_state state);
-	int (*cpu_on)(unsigned long cpuid, unsigned long entry_point);
-	int (*migrate)(unsigned long cpuid);
-};
-
-extern struct psci_operations psci_ops;
-
 int psci_init(void);
 
 #endif /* __ASM_PSCI_H */
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index 4b8023c5d146..a498f2cd2c2a 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -60,21 +60,14 @@ struct secondary_data {
 	void *stack;
 };
 extern struct secondary_data secondary_data;
-extern void secondary_holding_pen(void);
-extern volatile unsigned long secondary_holding_pen_release;
+extern void secondary_entry(void);
 
 extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
-struct device_node;
+extern int __cpu_disable(void);
 
-struct smp_enable_ops {
-	const char	*name;
-	int		(*init_cpu)(struct device_node *, int);
-	int		(*prepare_cpu)(int);
-};
-
-extern const struct smp_enable_ops smp_spin_table_ops;
-extern const struct smp_enable_ops smp_psci_ops;
+extern void __cpu_die(unsigned int cpu);
+extern void cpu_die(void);
 
 #endif /* ifndef __ASM_SMP_H */
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
new file mode 100644
index 000000000000..983fa7c153a2
--- /dev/null
+++ b/arch/arm64/include/asm/topology.h
@@ -0,0 +1,73 @@
+#ifndef _ASM_ARM_TOPOLOGY_H
+#define _ASM_ARM_TOPOLOGY_H
+
+#ifdef CONFIG_ARM_CPU_TOPOLOGY
+
+#include <linux/cpumask.h>
+
+struct cputopo_arm {
+	int thread_id;
+	int core_id;
+	int socket_id;
+	cpumask_t thread_sibling;
+	cpumask_t core_sibling;
+};
+
+extern struct cputopo_arm cpu_topology[NR_CPUS];
+
+#define topology_physical_package_id(cpu)	(cpu_topology[cpu].socket_id)
+#define topology_core_id(cpu)		(cpu_topology[cpu].core_id)
+#define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
+#define topology_thread_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
+
+#define mc_capable()	(cpu_topology[0].socket_id != -1)
+#define smt_capable()	(cpu_topology[0].thread_id != -1)
+
+void init_cpu_topology(void);
+void store_cpu_topology(unsigned int cpuid);
+const struct cpumask *cpu_coregroup_mask(int cpu);
+int cluster_to_logical_mask(unsigned int socket_id, cpumask_t *cluster_mask);
+
+#ifdef CONFIG_DISABLE_CPU_SCHED_DOMAIN_BALANCE
+/* Common values for CPUs */
+#ifndef SD_CPU_INIT
+#define SD_CPU_INIT (struct sched_domain) {				\
+	.min_interval		= 1,					\
+	.max_interval		= 4,					\
+	.busy_factor		= 64,					\
+	.imbalance_pct		= 125,					\
+	.cache_nice_tries	= 1,					\
+	.busy_idx		= 2,					\
+	.idle_idx		= 1,					\
+	.newidle_idx		= 0,					\
+	.wake_idx		= 0,					\
+	.forkexec_idx		= 0,					\
+									\
+	.flags			= 0*SD_LOAD_BALANCE			\
+				| 1*SD_BALANCE_NEWIDLE			\
+				| 1*SD_BALANCE_EXEC			\
+				| 1*SD_BALANCE_FORK			\
+				| 0*SD_BALANCE_WAKE			\
+				| 1*SD_WAKE_AFFINE			\
+				| 0*SD_SHARE_CPUPOWER			\
+				| 0*SD_SHARE_PKG_RESOURCES		\
+				| 0*SD_SERIALIZE			\
+				,					\
+	.last_balance		 = jiffies,				\
+	.balance_interval	= 1,					\
+}
+#endif
+#endif /* CONFIG_DISABLE_CPU_SCHED_DOMAIN_BALANCE */
+
+#else
+
+static inline void init_cpu_topology(void) { }
+static inline void store_cpu_topology(unsigned int cpuid) { }
+static inline int cluster_to_logical_mask(unsigned int socket_id,
+	cpumask_t *cluster_mask) { return -EINVAL; }
+
+#endif
+
+#include <asm-generic/topology.h>
+
+#endif /* _ASM_ARM_TOPOLOGY_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 7b4b564961d4..2d145e38ad49 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -9,15 +9,16 @@ AFLAGS_head.o		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 arm64-obj-y		:= cputable.o debug-monitors.o entry.o irq.o fpsimd.o	\
 			   entry-fpsimd.o process.o ptrace.o setup.o signal.o	\
 			   sys.o stacktrace.o time.o traps.o io.o vdso.o	\
-			   hyp-stub.o psci.o
+			   hyp-stub.o psci.o cpu_ops.o
 
 arm64-obj-$(CONFIG_COMPAT)		+= sys32.o kuser32.o signal32.o 	\
 					   sys_compat.o
 arm64-obj-$(CONFIG_MODULES)		+= arm64ksyms.o module.o
-arm64-obj-$(CONFIG_SMP)			+= smp.o smp_spin_table.o smp_psci.o
+arm64-obj-$(CONFIG_SMP)			+= smp.o smp_spin_table.o
 arm64-obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o
 arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)+= hw_breakpoint.o
 arm64-obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
+arm64-obj-$(CONFIG_ARM_CPU_TOPOLOGY)  += topology.o
 
 obj-y					+= $(arm64-obj-y) vdso/
 obj-m					+= $(arm64-obj-m)
diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c
new file mode 100644
index 000000000000..04efea8fe4bc
--- /dev/null
+++ b/arch/arm64/kernel/cpu_ops.c
@@ -0,0 +1,99 @@
+/*
+ * CPU kernel entry/exit control
+ *
+ * Copyright (C) 2013 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <asm/cpu_ops.h>
+#include <asm/smp_plat.h>
+#include <linux/errno.h>
+#include <linux/of.h>
+#include <linux/string.h>
+
+extern const struct cpu_operations smp_spin_table_ops;
+extern const struct cpu_operations cpu_psci_ops;
+
+const struct cpu_operations *cpu_ops[NR_CPUS];
+
+static const struct cpu_operations *supported_cpu_ops[] __initconst = {
+#ifdef CONFIG_SMP
+	&smp_spin_table_ops,
+	&cpu_psci_ops,
+#endif
+	NULL,
+};
+
+static const struct cpu_operations * __init cpu_get_ops(const char *name)
+{
+	const struct cpu_operations **ops = supported_cpu_ops;
+
+	while (*ops) {
+		if (!strcmp(name, (*ops)->name))
+			return *ops;
+
+		ops++;
+	}
+
+	return NULL;
+}
+
+/*
+ * Read a cpu's enable method from the device tree and record it in cpu_ops.
+ */
+int __init cpu_read_ops(struct device_node *dn, int cpu)
+{
+	const char *enable_method = of_get_property(dn, "enable-method", NULL);
+	if (!enable_method) {
+		/*
+		 * The boot CPU may not have an enable method (e.g. when
+		 * spin-table is used for secondaries). Don't warn spuriously.
+		 */
+		if (cpu != 0)
+			pr_err("%s: missing enable-method property\n",
+				dn->full_name);
+		return -ENOENT;
+	}
+
+	cpu_ops[cpu] = cpu_get_ops(enable_method);
+	if (!cpu_ops[cpu]) {
+		pr_warn("%s: unsupported enable-method property: %s\n",
+			dn->full_name, enable_method);
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+void __init cpu_read_bootcpu_ops(void)
+{
+	struct device_node *dn = NULL;
+	u64 mpidr = cpu_logical_map(0);
+
+	while ((dn = of_find_node_by_type(dn, "cpu"))) {
+		u64 hwid;
+		const __be32 *prop;
+
+		prop = of_get_property(dn, "reg", NULL);
+		if (!prop)
+			continue;
+
+		hwid = of_read_number(prop, of_n_addr_cells(dn));
+		if (hwid == mpidr) {
+			cpu_read_ops(dn, 0);
+			of_node_put(dn);
+			return;
+		}
+	}
+}
diff --git a/arch/arm64/kernel/cputable.c b/arch/arm64/kernel/cputable.c
index 63cfc4a43f4e..fd3993cb060f 100644
--- a/arch/arm64/kernel/cputable.c
+++ b/arch/arm64/kernel/cputable.c
@@ -22,7 +22,7 @@
 
 extern unsigned long __cpu_setup(void);
 
-struct cpu_info __initdata cpu_table[] = {
+struct cpu_info cpu_table[] = {
 	{
 		.cpu_id_val	= 0x000f0000,
 		.cpu_id_mask	= 0x000f0000,
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 53dcae49e729..3532ca613718 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -217,7 +217,6 @@ ENTRY(__boot_cpu_mode)
 	.quad	PAGE_OFFSET
 
 #ifdef CONFIG_SMP
-	.pushsection    .smp.pen.text, "ax"
 	.align	3
 1:	.quad	.
 	.quad	secondary_holding_pen_release
@@ -242,7 +241,16 @@ pen:	ldr	x4, [x3]
 	wfe
 	b	pen
 ENDPROC(secondary_holding_pen)
-	.popsection
+
+	/*
+	 * Secondary entry point that jumps straight into the kernel. Only to
+	 * be used where CPUs are brought online dynamically by the kernel.
+	 */
+ENTRY(secondary_entry)
+	bl	__calc_phys_offset		// x2=phys offset
+	bl	el2_setup			// Drop to EL1
+	b	secondary_startup
+ENDPROC(secondary_entry)
 
 ENTRY(secondary_startup)
 	/*
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index ecb3354292ed..473e5dbf8f39 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -81,3 +81,64 @@ void __init init_IRQ(void)
 	if (!handle_arch_irq)
 		panic("No interrupt controller found.");
 }
+
+#ifdef CONFIG_HOTPLUG_CPU
+static bool migrate_one_irq(struct irq_desc *desc)
+{
+	struct irq_data *d = irq_desc_get_irq_data(desc);
+	const struct cpumask *affinity = d->affinity;
+	struct irq_chip *c;
+	bool ret = false;
+
+	/*
+	 * If this is a per-CPU interrupt, or the affinity does not
+	 * include this CPU, then we have nothing to do.
+	 */
+	if (irqd_is_per_cpu(d) || !cpumask_test_cpu(smp_processor_id(), affinity))
+		return false;
+
+	if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
+		affinity = cpu_online_mask;
+		ret = true;
+	}
+
+	c = irq_data_get_irq_chip(d);
+	if (!c->irq_set_affinity)
+		pr_debug("IRQ%u: unable to set affinity\n", d->irq);
+	else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret)
+		cpumask_copy(d->affinity, affinity);
+
+	return ret;
+}
+
+/*
+ * The current CPU has been marked offline.  Migrate IRQs off this CPU.
+ * If the affinity settings do not allow other CPUs, force them onto any
+ * available CPU.
+ *
+ * Note: we must iterate over all IRQs, whether they have an attached
+ * action structure or not, as we need to get chained interrupts too.
+ */
+void migrate_irqs(void)
+{
+	unsigned int i;
+	struct irq_desc *desc;
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	for_each_irq_desc(i, desc) {
+		bool affinity_broken;
+
+		raw_spin_lock(&desc->lock);
+		affinity_broken = migrate_one_irq(desc);
+		raw_spin_unlock(&desc->lock);
+
+		if (affinity_broken)
+			pr_warn_ratelimited("IRQ%u no longer affine to CPU%u\n",
+					    i, smp_processor_id());
+	}
+
+	local_irq_restore(flags);
+}
+#endif /* CONFIG_HOTPLUG_CPU */
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 46f02c3b5015..4caf198ca44f 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -102,6 +102,13 @@ void arch_cpu_idle(void)
 	local_irq_enable();
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+void arch_cpu_idle_dead(void)
+{
+       cpu_die();
+}
+#endif
+
 void machine_shutdown(void)
 {
 #ifdef CONFIG_SMP
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index 14f73c445ff5..4f97db3d7363 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -17,12 +17,32 @@
 
 #include <linux/init.h>
 #include <linux/of.h>
+#include <linux/smp.h>
 
 #include <asm/compiler.h>
+#include <asm/cpu_ops.h>
 #include <asm/errno.h>
 #include <asm/psci.h>
+#include <asm/smp_plat.h>
 
-struct psci_operations psci_ops;
+#define PSCI_POWER_STATE_TYPE_STANDBY		0
+#define PSCI_POWER_STATE_TYPE_POWER_DOWN	1
+
+struct psci_power_state {
+	u16	id;
+	u8	type;
+	u8	affinity_level;
+};
+
+struct psci_operations {
+	int (*cpu_suspend)(struct psci_power_state state,
+			   unsigned long entry_point);
+	int (*cpu_off)(struct psci_power_state state);
+	int (*cpu_on)(unsigned long cpuid, unsigned long entry_point);
+	int (*migrate)(unsigned long cpuid);
+};
+
+static struct psci_operations psci_ops;
 
 static int (*invoke_psci_fn)(u64, u64, u64, u64);
 
@@ -209,3 +229,68 @@ int __init psci_init(void)
 	of_node_put(np);
 	return err;
 }
+
+#ifdef CONFIG_SMP
+
+static int __init cpu_psci_cpu_init(struct device_node *dn, unsigned int cpu)
+{
+	return 0;
+}
+
+static int __init cpu_psci_cpu_prepare(unsigned int cpu)
+{
+	if (!psci_ops.cpu_on) {
+		pr_err("no cpu_on method, not booting CPU%d\n", cpu);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static int cpu_psci_cpu_boot(unsigned int cpu)
+{
+	int err = psci_ops.cpu_on(cpu_logical_map(cpu), __pa(secondary_entry));
+	if (err)
+		pr_err("psci: failed to boot CPU%d (%d)\n", cpu, err);
+
+	return err;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int cpu_psci_cpu_disable(unsigned int cpu)
+{
+	/* Fail early if we don't have CPU_OFF support */
+	if (!psci_ops.cpu_off)
+		return -EOPNOTSUPP;
+	return 0;
+}
+
+static void cpu_psci_cpu_die(unsigned int cpu)
+{
+	int ret;
+	/*
+	 * There are no known implementations of PSCI actually using the
+	 * power state field, pass a sensible default for now.
+	 */
+	struct psci_power_state state = {
+		.type = PSCI_POWER_STATE_TYPE_POWER_DOWN,
+	};
+
+	ret = psci_ops.cpu_off(state);
+
+	pr_crit("psci: unable to power off CPU%u (%d)\n", cpu, ret);
+}
+#endif
+
+const struct cpu_operations cpu_psci_ops = {
+	.name		= "psci",
+	.cpu_init	= cpu_psci_cpu_init,
+	.cpu_prepare	= cpu_psci_cpu_prepare,
+	.cpu_boot	= cpu_psci_cpu_boot,
+#ifdef CONFIG_HOTPLUG_CPU
+	.cpu_disable	= cpu_psci_cpu_disable,
+	.cpu_die	= cpu_psci_cpu_die,
+#endif
+};
+
+#endif
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index add6ea616843..85afdae9cc05 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -45,6 +45,7 @@
 #include <asm/cputype.h>
 #include <asm/elf.h>
 #include <asm/cputable.h>
+#include <asm/cpu_ops.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/smp_plat.h>
@@ -97,6 +98,11 @@ void __init early_print(const char *str, ...)
 	printk("%s", buf);
 }
 
+bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
+{
+	return phys_id == cpu_logical_map(cpu);
+}
+
 static void __init setup_processor(void)
 {
 	struct cpu_info *cpu_info;
@@ -269,6 +275,7 @@ void __init setup_arch(char **cmdline_p)
 	psci_init();
 
 	cpu_logical_map(0) = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
+	cpu_read_bootcpu_ops();
 #ifdef CONFIG_SMP
 	smp_init_cpus();
 #endif
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index a28d2859932e..5e9d27442fbb 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -39,6 +39,7 @@
 #include <asm/atomic.h>
 #include <asm/cacheflush.h>
 #include <asm/cputype.h>
+#include <asm/cpu_ops.h>
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -57,7 +58,6 @@
  * where to place its SVC stack
  */
 struct secondary_data secondary_data;
-volatile unsigned long secondary_holding_pen_release = INVALID_HWID;
 
 enum ipi_msg_type {
 	IPI_RESCHEDULE,
@@ -66,61 +66,16 @@ enum ipi_msg_type {
 	IPI_CPU_STOP,
 };
 
-static DEFINE_RAW_SPINLOCK(boot_lock);
-
-/*
- * Write secondary_holding_pen_release in a way that is guaranteed to be
- * visible to all observers, irrespective of whether they're taking part
- * in coherency or not.  This is necessary for the hotplug code to work
- * reliably.
- */
-static void __cpuinit write_pen_release(u64 val)
-{
-	void *start = (void *)&secondary_holding_pen_release;
-	unsigned long size = sizeof(secondary_holding_pen_release);
-
-	secondary_holding_pen_release = val;
-	__flush_dcache_area(start, size);
-}
-
 /*
  * Boot a secondary CPU, and assign it the specified idle task.
  * This also gives us the initial stack to use for this CPU.
  */
 static int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
-	unsigned long timeout;
+	if (cpu_ops[cpu]->cpu_boot)
+		return cpu_ops[cpu]->cpu_boot(cpu);
 
-	/*
-	 * Set synchronisation state between this boot processor
-	 * and the secondary one
-	 */
-	raw_spin_lock(&boot_lock);
-
-	/*
-	 * Update the pen release flag.
-	 */
-	write_pen_release(cpu_logical_map(cpu));
-
-	/*
-	 * Send an event, causing the secondaries to read pen_release.
-	 */
-	sev();
-
-	timeout = jiffies + (1 * HZ);
-	while (time_before(jiffies, timeout)) {
-		if (secondary_holding_pen_release == INVALID_HWID)
-			break;
-		udelay(10);
-	}
-
-	/*
-	 * Now the secondary core is starting up let it run its
-	 * calibrations, then wait for it to finish
-	 */
-	raw_spin_unlock(&boot_lock);
-
-	return secondary_holding_pen_release != INVALID_HWID ? -ENOSYS : 0;
+	return -EOPNOTSUPP;
 }
 
 static DECLARE_COMPLETION(cpu_running);
@@ -161,6 +116,11 @@ int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *idle)
 	return ret;
 }
 
+static void __cpuinit smp_store_cpu_info(unsigned int cpuid)
+{
+	store_cpu_topology(cpuid);
+}
+
 /*
  * This is the secondary CPU boot entry.  We're using this CPUs
  * idle thread stack, but a set of temporary page tables.
@@ -190,17 +150,8 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	preempt_disable();
 	trace_hardirqs_off();
 
-	/*
-	 * Let the primary processor know we're out of the
-	 * pen, then head off into the C entry point
-	 */
-	write_pen_release(INVALID_HWID);
-
-	/*
-	 * Synchronise with the boot thread.
-	 */
-	raw_spin_lock(&boot_lock);
-	raw_spin_unlock(&boot_lock);
+	if (cpu_ops[cpu]->cpu_postboot)
+		cpu_ops[cpu]->cpu_postboot();
 
 	/*
 	 * Enable local interrupts.
@@ -209,6 +160,8 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	local_irq_enable();
 	local_fiq_enable();
 
+	smp_store_cpu_info(cpu);
+
 	/*
 	 * OK, now it's safe to let the boot CPU continue.  Wait for
 	 * the CPU migration code to notice that the CPU is online
@@ -223,6 +176,102 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	cpu_startup_entry(CPUHP_ONLINE);
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+static int op_cpu_disable(unsigned int cpu)
+{
+	/*
+	 * If we don't have a cpu_die method, abort before we reach the point
+	 * of no return. CPU0 may not have an cpu_ops, so test for it.
+	 */
+	if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_die)
+		return -EOPNOTSUPP;
+
+	/*
+	 * We may need to abort a hot unplug for some other mechanism-specific
+	 * reason.
+	 */
+	if (cpu_ops[cpu]->cpu_disable)
+		return cpu_ops[cpu]->cpu_disable(cpu);
+
+	return 0;
+}
+
+/*
+ * __cpu_disable runs on the processor to be shutdown.
+ */
+int __cpu_disable(void)
+{
+	unsigned int cpu = smp_processor_id();
+	int ret;
+
+	ret = op_cpu_disable(cpu);
+	if (ret)
+		return ret;
+
+	/*
+	 * Take this CPU offline.  Once we clear this, we can't return,
+	 * and we must not schedule until we're ready to give up the cpu.
+	 */
+	set_cpu_online(cpu, false);
+
+	/*
+	 * OK - migrate IRQs away from this CPU
+	 */
+	migrate_irqs();
+
+	/*
+	 * Remove this CPU from the vm mask set of all processes.
+	 */
+	clear_tasks_mm_cpumask(cpu);
+
+	return 0;
+}
+
+static DECLARE_COMPLETION(cpu_died);
+
+/*
+ * called on the thread which is asking for a CPU to be shutdown -
+ * waits until shutdown has completed, or it is timed out.
+ */
+void __cpu_die(unsigned int cpu)
+{
+	if (!wait_for_completion_timeout(&cpu_died, msecs_to_jiffies(5000))) {
+		pr_crit("CPU%u: cpu didn't die\n", cpu);
+		return;
+	}
+	pr_notice("CPU%u: shutdown\n", cpu);
+}
+
+/*
+ * Called from the idle thread for the CPU which has been shutdown.
+ *
+ * Note that we disable IRQs here, but do not re-enable them
+ * before returning to the caller. This is also the behaviour
+ * of the other hotplug-cpu capable cores, so presumably coming
+ * out of idle fixes this.
+ */
+void cpu_die(void)
+{
+	unsigned int cpu = smp_processor_id();
+
+	idle_task_exit();
+
+	local_irq_disable();
+
+	/* Tell __cpu_die() that this CPU is now safe to dispose of */
+	complete(&cpu_died);
+
+	/*
+	 * Actually shutdown the CPU. This must never fail. The specific hotplug
+	 * mechanism must perform all required cache maintenance to ensure that
+	 * no dirty lines are lost in the process of shutting down the CPU.
+	 */
+	cpu_ops[cpu]->cpu_die(cpu);
+
+	BUG();
+}
+#endif
+
 void __init smp_cpus_done(unsigned int max_cpus)
 {
 	unsigned long bogosum = loops_per_jiffy * num_online_cpus();
@@ -238,28 +287,6 @@ void __init smp_prepare_boot_cpu(void)
 
 static void (*smp_cross_call)(const struct cpumask *, unsigned int);
 
-static const struct smp_enable_ops *enable_ops[] __initconst = {
-	&smp_spin_table_ops,
-	&smp_psci_ops,
-	NULL,
-};
-
-static const struct smp_enable_ops *smp_enable_ops[NR_CPUS];
-
-static const struct smp_enable_ops * __init smp_get_enable_ops(const char *name)
-{
-	const struct smp_enable_ops **ops = enable_ops;
-
-	while (*ops) {
-		if (!strcmp(name, (*ops)->name))
-			return *ops;
-
-		ops++;
-	}
-
-	return NULL;
-}
-
 /*
  * Enumerate the possible CPU set from the device tree and build the
  * cpu logical map array containing MPIDR values related to logical
@@ -267,9 +294,8 @@ static const struct smp_enable_ops * __init smp_get_enable_ops(const char *name)
  */
 void __init smp_init_cpus(void)
 {
-	const char *enable_method;
 	struct device_node *dn = NULL;
-	int i, cpu = 1;
+	unsigned int i, cpu = 1;
 	bool bootcpu_valid = false;
 
 	while ((dn = of_find_node_by_type(dn, "cpu"))) {
@@ -338,25 +364,10 @@ void __init smp_init_cpus(void)
 		if (cpu >= NR_CPUS)
 			goto next;
 
-		/*
-		 * We currently support only the "spin-table" enable-method.
-		 */
-		enable_method = of_get_property(dn, "enable-method", NULL);
-		if (!enable_method) {
-			pr_err("%s: missing enable-method property\n",
-				dn->full_name);
+		if (cpu_read_ops(dn, cpu) != 0)
 			goto next;
-		}
 
-		smp_enable_ops[cpu] = smp_get_enable_ops(enable_method);
-
-		if (!smp_enable_ops[cpu]) {
-			pr_err("%s: invalid enable-method property: %s\n",
-			       dn->full_name, enable_method);
-			goto next;
-		}
-
-		if (smp_enable_ops[cpu]->init_cpu(dn, cpu))
+		if (cpu_ops[cpu]->cpu_init(dn, cpu))
 			goto next;
 
 		pr_debug("cpu logical map 0x%llx\n", hwid);
@@ -386,8 +397,13 @@ void __init smp_init_cpus(void)
 
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
-	int cpu, err;
-	unsigned int ncores = num_possible_cpus();
+	int err;
+	unsigned int cpu, ncores = num_possible_cpus();
+
+	init_cpu_topology();
+
+	smp_store_cpu_info(smp_processor_id());
+
 
 	/*
 	 * are we trying to boot more cores than exist?
@@ -414,10 +430,10 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 		if (cpu == smp_processor_id())
 			continue;
 
-		if (!smp_enable_ops[cpu])
+		if (!cpu_ops[cpu])
 			continue;
 
-		err = smp_enable_ops[cpu]->prepare_cpu(cpu);
+		err = cpu_ops[cpu]->cpu_prepare(cpu);
 		if (err)
 			continue;
 
diff --git a/arch/arm64/kernel/smp_psci.c b/arch/arm64/kernel/smp_psci.c
deleted file mode 100644
index 0c533301be77..000000000000
--- a/arch/arm64/kernel/smp_psci.c
+++ /dev/null
@@ -1,53 +0,0 @@
-/*
- * PSCI SMP initialisation
- *
- * Copyright (C) 2013 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/init.h>
-#include <linux/of.h>
-#include <linux/smp.h>
-
-#include <asm/psci.h>
-#include <asm/smp_plat.h>
-
-static int __init smp_psci_init_cpu(struct device_node *dn, int cpu)
-{
-	return 0;
-}
-
-static int __init smp_psci_prepare_cpu(int cpu)
-{
-	int err;
-
-	if (!psci_ops.cpu_on) {
-		pr_err("psci: no cpu_on method, not booting CPU%d\n", cpu);
-		return -ENODEV;
-	}
-
-	err = psci_ops.cpu_on(cpu_logical_map(cpu), __pa(secondary_holding_pen));
-	if (err) {
-		pr_err("psci: failed to boot CPU%d (%d)\n", cpu, err);
-		return err;
-	}
-
-	return 0;
-}
-
-const struct smp_enable_ops smp_psci_ops __initconst = {
-	.name		= "psci",
-	.init_cpu	= smp_psci_init_cpu,
-	.prepare_cpu	= smp_psci_prepare_cpu,
-};
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 7c35fa682f76..27f08367a6e7 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -16,15 +16,39 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/of.h>
 #include <linux/smp.h>
 
 #include <asm/cacheflush.h>
+#include <asm/cpu_ops.h>
+#include <asm/cputype.h>
+#include <asm/smp_plat.h>
+
+extern void secondary_holding_pen(void);
+volatile unsigned long secondary_holding_pen_release = INVALID_HWID;
 
 static phys_addr_t cpu_release_addr[NR_CPUS];
+static DEFINE_RAW_SPINLOCK(boot_lock);
 
-static int __init smp_spin_table_init_cpu(struct device_node *dn, int cpu)
+/*
+ * Write secondary_holding_pen_release in a way that is guaranteed to be
+ * visible to all observers, irrespective of whether they're taking part
+ * in coherency or not.  This is necessary for the hotplug code to work
+ * reliably.
+ */
+static void write_pen_release(u64 val)
+{
+	void *start = (void *)&secondary_holding_pen_release;
+	unsigned long size = sizeof(secondary_holding_pen_release);
+
+	secondary_holding_pen_release = val;
+	__flush_dcache_area(start, size);
+}
+
+
+static int smp_spin_table_cpu_init(struct device_node *dn, unsigned int cpu)
 {
 	/*
 	 * Determine the address from which the CPU is polling.
@@ -40,7 +64,7 @@ static int __init smp_spin_table_init_cpu(struct device_node *dn, int cpu)
 	return 0;
 }
 
-static int __init smp_spin_table_prepare_cpu(int cpu)
+static int smp_spin_table_cpu_prepare(unsigned int cpu)
 {
 	void **release_addr;
 
@@ -59,8 +83,60 @@ static int __init smp_spin_table_prepare_cpu(int cpu)
 	return 0;
 }
 
-const struct smp_enable_ops smp_spin_table_ops __initconst = {
+static int smp_spin_table_cpu_boot(unsigned int cpu)
+{
+	unsigned long timeout;
+
+	/*
+	 * Set synchronisation state between this boot processor
+	 * and the secondary one
+	 */
+	raw_spin_lock(&boot_lock);
+
+	/*
+	 * Update the pen release flag.
+	 */
+	write_pen_release(cpu_logical_map(cpu));
+
+	/*
+	 * Send an event, causing the secondaries to read pen_release.
+	 */
+	sev();
+
+	timeout = jiffies + (1 * HZ);
+	while (time_before(jiffies, timeout)) {
+		if (secondary_holding_pen_release == INVALID_HWID)
+			break;
+		udelay(10);
+	}
+
+	/*
+	 * Now the secondary core is starting up let it run its
+	 * calibrations, then wait for it to finish
+	 */
+	raw_spin_unlock(&boot_lock);
+
+	return secondary_holding_pen_release != INVALID_HWID ? -ENOSYS : 0;
+}
+
+void smp_spin_table_cpu_postboot(void)
+{
+	/*
+	 * Let the primary processor know we're out of the pen.
+	 */
+	write_pen_release(INVALID_HWID);
+
+	/*
+	 * Synchronise with the boot thread.
+	 */
+	raw_spin_lock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
+}
+
+const struct cpu_operations smp_spin_table_ops = {
 	.name		= "spin-table",
-	.init_cpu 	= smp_spin_table_init_cpu,
-	.prepare_cpu	= smp_spin_table_prepare_cpu,
+	.cpu_init	= smp_spin_table_cpu_init,
+	.cpu_prepare	= smp_spin_table_cpu_prepare,
+	.cpu_boot	= smp_spin_table_cpu_boot,
+	.cpu_postboot	= smp_spin_table_cpu_postboot,
 };
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
new file mode 100644
index 000000000000..971064a0c6b4
--- /dev/null
+++ b/arch/arm64/kernel/topology.c
@@ -0,0 +1,537 @@
+/*
+ * arch/arm64/kernel/topology.c
+ *
+ * Copyright (C) 2011,2013 Linaro Limited.
+ * Written by: Vincent Guittot
+ *
+ * based on arch/sh/kernel/topology.c
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/node.h>
+#include <linux/nodemask.h>
+#include <linux/of.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#include <asm/cputype.h>
+#include <asm/smp_plat.h>
+#include <asm/topology.h>
+
+/*
+ * cpu power scale management
+ */
+
+/*
+ * cpu power table
+ * This per cpu data structure describes the relative capacity of each core.
+ * On a heteregenous system, cores don't have the same computation capacity
+ * and we reflect that difference in the cpu_power field so the scheduler can
+ * take this difference into account during load balance. A per cpu structure
+ * is preferred because each CPU updates its own cpu_power field during the
+ * load balance except for idle cores. One idle core is selected to run the
+ * rebalance_domains for all idle cores and the cpu_power can be updated
+ * during this sequence.
+ */
+static DEFINE_PER_CPU(unsigned long, cpu_scale);
+
+unsigned long arch_scale_freq_power(struct sched_domain *sd, int cpu)
+{
+	return per_cpu(cpu_scale, cpu);
+}
+
+static void set_power_scale(unsigned int cpu, unsigned long power)
+{
+	per_cpu(cpu_scale, cpu) = power;
+}
+
+#ifdef CONFIG_OF
+struct cpu_efficiency {
+	const char *compatible;
+	unsigned long efficiency;
+};
+
+/*
+ * Table of relative efficiency of each processors
+ * The efficiency value must fit in 20bit and the final
+ * cpu_scale value must be in the range
+ *   0 < cpu_scale < 3*SCHED_POWER_SCALE/2
+ * in order to return at most 1 when DIV_ROUND_CLOSEST
+ * is used to compute the capacity of a CPU.
+ * Processors that are not defined in the table,
+ * use the default SCHED_POWER_SCALE value for cpu_scale.
+ */
+static const struct cpu_efficiency table_efficiency[] = {
+	{ "arm,cortex-a57", 3891 },
+	{ "arm,cortex-a53", 2048 },
+	{ NULL, },
+};
+
+static unsigned long *__cpu_capacity;
+#define cpu_capacity(cpu)	__cpu_capacity[cpu]
+
+static unsigned long middle_capacity = 1;
+static int cluster_id;
+
+static int __init get_cpu_for_node(struct device_node *node)
+{
+	struct device_node *cpu_node;
+	int cpu;
+
+	cpu_node = of_parse_phandle(node, "cpu", 0);
+	if (!cpu_node) {
+		pr_crit("%s: Unable to parse CPU phandle\n", node->full_name);
+		return -1;
+	}
+
+	for_each_possible_cpu(cpu) {
+		if (of_get_cpu_node(cpu, NULL) == cpu_node)
+			return cpu;
+	}
+
+	pr_crit("Unable to find CPU node for %s\n", cpu_node->full_name);
+	return -1;
+}
+
+static void __init parse_core(struct device_node *core, int core_id)
+{
+	char name[10];
+	bool leaf = true;
+	int i, cpu;
+	struct device_node *t;
+
+	i = 0;
+	do {
+		snprintf(name, sizeof(name), "thread%d", i);
+		t = of_get_child_by_name(core, name);
+		if (t) {
+			leaf = false;
+			cpu = get_cpu_for_node(t);
+			if (cpu) {
+				pr_info("CPU%d: socket %d core %d thread %d\n",
+					cpu, cluster_id, core_id, i);
+				cpu_topology[cpu].socket_id = cluster_id;
+				cpu_topology[cpu].core_id = core_id;
+				cpu_topology[cpu].thread_id = i;
+			} else {
+				pr_err("%s: Can't get CPU for thread\n",
+				       t->full_name);
+			}
+		}
+		i++;
+	} while (t);
+
+	cpu = get_cpu_for_node(core);
+	if (cpu >= 0) {
+		if (!leaf) {
+			pr_err("%s: Core has both threads and CPU\n",
+			       core->full_name);
+			return;
+		}
+
+		pr_info("CPU%d: socket %d core %d\n",
+			cpu, cluster_id, core_id);
+		cpu_topology[cpu].socket_id = cluster_id;
+		cpu_topology[cpu].core_id = core_id;
+	} else if (leaf) {
+		pr_err("%s: Can't get CPU for leaf core\n", core->full_name);
+	}
+}
+
+static void __init parse_cluster(struct device_node *cluster)
+{
+	char name[10];
+	bool leaf = true;
+	bool has_cores = false;
+	struct device_node *c;
+	int core_id = 0;
+	int i;
+
+	/*
+	 * First check for child clusters; we currently ignore any
+	 * information about the nesting of clusters and present the
+	 * scheduler with a flat list of them.
+	 */
+	i = 0;
+	do {
+		snprintf(name, sizeof(name), "cluster%d", i);
+		c = of_get_child_by_name(cluster, name);
+		if (c) {
+			parse_cluster(c);
+			leaf = false;
+		}
+		i++;
+	} while (c);
+
+	/* Now check for cores */
+	i = 0;
+	do {
+		snprintf(name, sizeof(name), "core%d", i);
+		c = of_get_child_by_name(cluster, name);
+		if (c) {
+			has_cores = true;
+
+			if (leaf)
+				parse_core(c, core_id++);
+			else
+				pr_err("%s: Non-leaf cluster with core %s\n",
+				       cluster->full_name, name);
+		}
+		i++;
+	} while (c);
+
+	if (leaf && !has_cores)
+		pr_warn("%s: empty cluster\n", cluster->full_name);
+
+	if (leaf)
+		cluster_id++;
+}
+
+/*
+ * Iterate all CPUs' descriptor in DT and compute the efficiency
+ * (as per table_efficiency). Also calculate a middle efficiency
+ * as close as possible to  (max{eff_i} - min{eff_i}) / 2
+ * This is later used to scale the cpu_power field such that an
+ * 'average' CPU is of middle power. Also see the comments near
+ * table_efficiency[] and update_cpu_power().
+ */
+static void __init parse_dt_topology(void)
+{
+	const struct cpu_efficiency *cpu_eff;
+	struct device_node *cn = NULL;
+	unsigned long min_capacity = (unsigned long)(-1);
+	unsigned long max_capacity = 0;
+	unsigned long capacity = 0;
+	int alloc_size, cpu;
+
+	alloc_size = nr_cpu_ids * sizeof(*__cpu_capacity);
+	__cpu_capacity = kzalloc(alloc_size, GFP_NOWAIT);
+
+	cn = of_find_node_by_path("/cpus");
+	if (!cn) {
+		pr_err("No CPU information found in DT\n");
+		return;
+	}
+
+	/*
+	 * If topology is provided as a cpu-map it is essentially a
+	 * root cluster.
+	 */
+	cn = of_find_node_by_name(cn, "cpu-map");
+	if (!cn)
+		return;
+	parse_cluster(cn);
+
+	for_each_possible_cpu(cpu) {
+		const u32 *rate;
+		int len;
+
+		/* Too early to use cpu->of_node */
+		cn = of_get_cpu_node(cpu, NULL);
+		if (!cn) {
+			pr_err("Missing device node for CPU %d\n", cpu);
+			continue;
+		}
+
+		/* check if the cpu is marked as "disabled", if so ignore */
+		if (!of_device_is_available(cn))
+			continue;
+
+		for (cpu_eff = table_efficiency; cpu_eff->compatible; cpu_eff++)
+			if (of_device_is_compatible(cn, cpu_eff->compatible))
+				break;
+
+		if (cpu_eff->compatible == NULL) {
+			pr_warn("%s: Unknown CPU type\n", cn->full_name);
+			continue;
+		}
+
+		rate = of_get_property(cn, "clock-frequency", &len);
+		if (!rate || len != 4) {
+			pr_err("%s: Missing clock-frequency property\n",
+				cn->full_name);
+			continue;
+		}
+
+		capacity = ((be32_to_cpup(rate)) >> 20) * cpu_eff->efficiency;
+
+		/* Save min capacity of the system */
+		if (capacity < min_capacity)
+			min_capacity = capacity;
+
+		/* Save max capacity of the system */
+		if (capacity > max_capacity)
+			max_capacity = capacity;
+
+		cpu_capacity(cpu) = capacity;
+	}
+
+	/* If min and max capacities are equal we bypass the update of the
+	 * cpu_scale because all CPUs have the same capacity. Otherwise, we
+	 * compute a middle_capacity factor that will ensure that the capacity
+	 * of an 'average' CPU of the system will be as close as possible to
+	 * SCHED_POWER_SCALE, which is the default value, but with the
+	 * constraint explained near table_efficiency[].
+	 */
+	if (min_capacity == max_capacity)
+		return;
+	else if (4 * max_capacity < (3 * (max_capacity + min_capacity)))
+		middle_capacity = (min_capacity + max_capacity)
+				>> (SCHED_POWER_SHIFT+1);
+	else
+		middle_capacity = ((max_capacity / 3)
+				>> (SCHED_POWER_SHIFT-1)) + 1;
+
+}
+
+/*
+ * Look for a customed capacity of a CPU in the cpu_topo_data table during the
+ * boot. The update of all CPUs is in O(n^2) for heteregeneous system but the
+ * function returns directly for SMP system.
+ */
+static void update_cpu_power(unsigned int cpu)
+{
+	if (!cpu_capacity(cpu))
+		return;
+
+	set_power_scale(cpu, cpu_capacity(cpu) / middle_capacity);
+
+	pr_info("CPU%u: update cpu_power %lu\n",
+		cpu, arch_scale_freq_power(NULL, cpu));
+}
+
+#else
+static inline void parse_dt_topology(void) {}
+static inline void update_cpu_power(unsigned int cpuid) {}
+#endif
+
+/*
+ * cpu topology table
+ */
+struct cputopo_arm cpu_topology[NR_CPUS];
+EXPORT_SYMBOL_GPL(cpu_topology);
+
+const struct cpumask *cpu_coregroup_mask(int cpu)
+{
+	return &cpu_topology[cpu].core_sibling;
+}
+
+static void update_siblings_masks(unsigned int cpuid)
+{
+	struct cputopo_arm *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
+	int cpu;
+
+	/* update core and thread sibling masks */
+	for_each_possible_cpu(cpu) {
+		cpu_topo = &cpu_topology[cpu];
+
+		if (cpuid_topo->socket_id != cpu_topo->socket_id)
+			continue;
+
+		cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
+		if (cpu != cpuid)
+			cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
+
+		if (cpuid_topo->core_id != cpu_topo->core_id)
+			continue;
+
+		cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling);
+		if (cpu != cpuid)
+			cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
+	}
+	smp_wmb();
+}
+
+void store_cpu_topology(unsigned int cpuid)
+{
+	struct cputopo_arm *cpuid_topo = &cpu_topology[cpuid];
+
+	/* DT should have been parsed by the time we get here */
+	if (cpuid_topo->core_id == -1)
+		pr_info("CPU%u: No topology information configured\n", cpuid);
+	else
+		update_siblings_masks(cpuid);
+
+	update_cpu_power(cpuid);
+}
+
+#ifdef CONFIG_SCHED_HMP
+
+/*
+ * Retrieve logical cpu index corresponding to a given MPIDR[23:0]
+ *  - mpidr: MPIDR[23:0] to be used for the look-up
+ *
+ * Returns the cpu logical index or -EINVAL on look-up error
+ */
+static inline int get_logical_index(u32 mpidr)
+{
+	int cpu;
+	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
+		if (cpu_logical_map(cpu) == mpidr)
+			return cpu;
+	return -EINVAL;
+}
+
+static const char * const little_cores[] = {
+	"arm,cortex-a53",
+	NULL,
+};
+
+static bool is_little_cpu(struct device_node *cn)
+{
+	const char * const *lc;
+	for (lc = little_cores; *lc; lc++)
+		if (of_device_is_compatible(cn, *lc))
+			return true;
+	return false;
+}
+
+void __init arch_get_fast_and_slow_cpus(struct cpumask *fast,
+					struct cpumask *slow)
+{
+	struct device_node *cn = NULL;
+	int cpu;
+
+	cpumask_clear(fast);
+	cpumask_clear(slow);
+
+	/*
+	 * Use the config options if they are given. This helps testing
+	 * HMP scheduling on systems without a big.LITTLE architecture.
+	 */
+	if (strlen(CONFIG_HMP_FAST_CPU_MASK) && strlen(CONFIG_HMP_SLOW_CPU_MASK)) {
+		if (cpulist_parse(CONFIG_HMP_FAST_CPU_MASK, fast))
+			WARN(1, "Failed to parse HMP fast cpu mask!\n");
+		if (cpulist_parse(CONFIG_HMP_SLOW_CPU_MASK, slow))
+			WARN(1, "Failed to parse HMP slow cpu mask!\n");
+		return;
+	}
+
+	/*
+	 * Else, parse device tree for little cores.
+	 */
+	while ((cn = of_find_node_by_type(cn, "cpu"))) {
+
+		const u32 *mpidr;
+		int len;
+
+		mpidr = of_get_property(cn, "reg", &len);
+		if (!mpidr || len != 8) {
+			pr_err("%s missing reg property\n", cn->full_name);
+			continue;
+		}
+
+		cpu = get_logical_index(be32_to_cpup(mpidr+1));
+		if (cpu == -EINVAL) {
+			pr_err("couldn't get logical index for mpidr %x\n",
+							be32_to_cpup(mpidr+1));
+			break;
+		}
+
+		if (is_little_cpu(cn))
+			cpumask_set_cpu(cpu, slow);
+		else
+			cpumask_set_cpu(cpu, fast);
+	}
+
+	if (!cpumask_empty(fast) && !cpumask_empty(slow))
+		return;
+
+	/*
+	 * We didn't find both big and little cores so let's call all cores
+	 * fast as this will keep the system running, with all cores being
+	 * treated equal.
+	 */
+	cpumask_setall(fast);
+	cpumask_clear(slow);
+}
+
+struct cpumask hmp_slow_cpu_mask;
+
+void __init arch_get_hmp_domains(struct list_head *hmp_domains_list)
+{
+	struct cpumask hmp_fast_cpu_mask;
+	struct hmp_domain *domain;
+
+	arch_get_fast_and_slow_cpus(&hmp_fast_cpu_mask, &hmp_slow_cpu_mask);
+
+	/*
+	 * Initialize hmp_domains
+	 * Must be ordered with respect to compute capacity.
+	 * Fastest domain at head of list.
+	 */
+	if(!cpumask_empty(&hmp_slow_cpu_mask)) {
+		domain = (struct hmp_domain *)
+			kmalloc(sizeof(struct hmp_domain), GFP_KERNEL);
+		cpumask_copy(&domain->possible_cpus, &hmp_slow_cpu_mask);
+		cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus);
+		list_add(&domain->hmp_domains, hmp_domains_list);
+	}
+	domain = (struct hmp_domain *)
+		kmalloc(sizeof(struct hmp_domain), GFP_KERNEL);
+	cpumask_copy(&domain->possible_cpus, &hmp_fast_cpu_mask);
+	cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus);
+	list_add(&domain->hmp_domains, hmp_domains_list);
+}
+#endif /* CONFIG_SCHED_HMP */
+
+/*
+ * cluster_to_logical_mask - return cpu logical mask of CPUs in a cluster
+ * @socket_id:		cluster HW identifier
+ * @cluster_mask:	the cpumask location to be initialized, modified by the
+ *			function only if return value == 0
+ *
+ * Return:
+ *
+ * 0 on success
+ * -EINVAL if cluster_mask is NULL or there is no record matching socket_id
+ */
+int cluster_to_logical_mask(unsigned int socket_id, cpumask_t *cluster_mask)
+{
+	int cpu;
+
+	if (!cluster_mask)
+		return -EINVAL;
+
+	for_each_online_cpu(cpu) {
+		if (socket_id == topology_physical_package_id(cpu)) {
+			cpumask_copy(cluster_mask, topology_core_cpumask(cpu));
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
+/*
+ * init_cpu_topology is called at boot when only one cpu is running
+ * which prevent simultaneous write access to cpu_topology array
+ */
+void __init init_cpu_topology(void)
+{
+	unsigned int cpu;
+
+	/* init core mask and power*/
+	for_each_possible_cpu(cpu) {
+		struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]);
+
+		cpu_topo->thread_id = -1;
+		cpu_topo->core_id =  -1;
+		cpu_topo->socket_id = -1;
+		cpumask_clear(&cpu_topo->core_sibling);
+		cpumask_clear(&cpu_topo->thread_sibling);
+
+		set_power_scale(cpu, SCHED_POWER_SCALE);
+	}
+	smp_wmb();
+
+	parse_dt_topology();
+}
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 3fae2be8b016..2c8a95b539ce 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -41,7 +41,6 @@ SECTIONS
 	}
 	.text : {			/* Real text segment		*/
 		_stext = .;		/* Text and read-only data	*/
-			*(.smp.pen.text)
 			__exception_text_start = .;
 			*(.exception.text)
 			__exception_text_end = .;
diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c
index 5dfd248e3f1a..0d3a9d4927b5 100644
--- a/arch/parisc/kernel/sys_parisc.c
+++ b/arch/parisc/kernel/sys_parisc.c
@@ -61,8 +61,15 @@ static int get_offset(struct address_space *mapping)
 	return (unsigned long) mapping >> 8;
 }
 
-static unsigned long get_shared_area(struct address_space *mapping,
-		unsigned long addr, unsigned long len, unsigned long pgoff)
+static unsigned long shared_align_offset(struct file *filp, unsigned long pgoff)
+{
+	struct address_space *mapping = filp ? filp->f_mapping : NULL;
+
+	return (get_offset(mapping) + pgoff) << PAGE_SHIFT;
+}
+
+static unsigned long get_shared_area(struct file *filp, unsigned long addr,
+		unsigned long len, unsigned long pgoff)
 {
 	struct vm_unmapped_area_info info;
 
@@ -71,7 +78,7 @@ static unsigned long get_shared_area(struct address_space *mapping,
 	info.low_limit = PAGE_ALIGN(addr);
 	info.high_limit = TASK_SIZE;
 	info.align_mask = PAGE_MASK & (SHMLBA - 1);
-	info.align_offset = (get_offset(mapping) + pgoff) << PAGE_SHIFT;
+	info.align_offset = shared_align_offset(filp, pgoff);
 	return vm_unmapped_area(&info);
 }
 
@@ -82,20 +89,18 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		return -ENOMEM;
 	if (flags & MAP_FIXED) {
 		if ((flags & MAP_SHARED) &&
-		    (addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1))
+		    (addr - shared_align_offset(filp, pgoff)) & (SHMLBA - 1))
 			return -EINVAL;
 		return addr;
 	}
 	if (!addr)
 		addr = TASK_UNMAPPED_BASE;
 
-	if (filp) {
-		addr = get_shared_area(filp->f_mapping, addr, len, pgoff);
-	} else if(flags & MAP_SHARED) {
-		addr = get_shared_area(NULL, addr, len, pgoff);
-	} else {
+	if (filp || (flags & MAP_SHARED))
+		addr = get_shared_area(filp, addr, len, pgoff);
+	else
 		addr = get_unshared_area(addr, len);
-	}
+
 	return addr;
 }
 
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index bc2da154f68b..ac204e022922 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -43,9 +43,6 @@ void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop,
 
 extern void kdump_move_device_tree(void);
 
-/* CPU OF node matching */
-struct device_node *of_get_cpu_node(int cpu, unsigned int *thread);
-
 /* cache lookup */
 struct device_node *of_find_next_cache_node(struct device_node *np);
 
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 8b6f7a99cce2..00610a34fb9a 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -827,49 +827,10 @@ static int __init prom_reconfig_setup(void)
 __initcall(prom_reconfig_setup);
 #endif
 
-/* Find the device node for a given logical cpu number, also returns the cpu
- * local thread number (index in ibm,interrupt-server#s) if relevant and
- * asked for (non NULL)
- */
-struct device_node *of_get_cpu_node(int cpu, unsigned int *thread)
+bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
 {
-	int hardid;
-	struct device_node *np;
-
-	hardid = get_hard_smp_processor_id(cpu);
-
-	for_each_node_by_type(np, "cpu") {
-		const u32 *intserv;
-		unsigned int plen, t;
-
-		/* Check for ibm,ppc-interrupt-server#s. If it doesn't exist
-		 * fallback to "reg" property and assume no threads
-		 */
-		intserv = of_get_property(np, "ibm,ppc-interrupt-server#s",
-				&plen);
-		if (intserv == NULL) {
-			const u32 *reg = of_get_property(np, "reg", NULL);
-			if (reg == NULL)
-				continue;
-			if (*reg == hardid) {
-				if (thread)
-					*thread = 0;
-				return np;
-			}
-		} else {
-			plen /= sizeof(u32);
-			for (t = 0; t < plen; t++) {
-				if (hardid == intserv[t]) {
-					if (thread)
-						*thread = t;
-					return np;
-				}
-			}
-		}
-	}
-	return NULL;
+	return (int)phys_id == get_hard_smp_processor_id(cpu);
 }
-EXPORT_SYMBOL(of_get_cpu_node);
 
 #if defined(CONFIG_DEBUG_FS) && defined(DEBUG)
 static struct debugfs_blob_wrapper flat_dt_blob;
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index 2e4b5be31a1b..94e20dd2729f 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -55,8 +55,7 @@ struct pcc_param {
 
 struct s390_xts_ctx {
 	u8 key[32];
-	u8 xts_param[16];
-	struct pcc_param pcc;
+	u8 pcc_key[32];
 	long enc;
 	long dec;
 	int key_len;
@@ -591,7 +590,7 @@ static int xts_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 		xts_ctx->enc = KM_XTS_128_ENCRYPT;
 		xts_ctx->dec = KM_XTS_128_DECRYPT;
 		memcpy(xts_ctx->key + 16, in_key, 16);
-		memcpy(xts_ctx->pcc.key + 16, in_key + 16, 16);
+		memcpy(xts_ctx->pcc_key + 16, in_key + 16, 16);
 		break;
 	case 48:
 		xts_ctx->enc = 0;
@@ -602,7 +601,7 @@ static int xts_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 		xts_ctx->enc = KM_XTS_256_ENCRYPT;
 		xts_ctx->dec = KM_XTS_256_DECRYPT;
 		memcpy(xts_ctx->key, in_key, 32);
-		memcpy(xts_ctx->pcc.key, in_key + 32, 32);
+		memcpy(xts_ctx->pcc_key, in_key + 32, 32);
 		break;
 	default:
 		*flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
@@ -621,29 +620,33 @@ static int xts_aes_crypt(struct blkcipher_desc *desc, long func,
 	unsigned int nbytes = walk->nbytes;
 	unsigned int n;
 	u8 *in, *out;
-	void *param;
+	struct pcc_param pcc_param;
+	struct {
+		u8 key[32];
+		u8 init[16];
+	} xts_param;
 
 	if (!nbytes)
 		goto out;
 
-	memset(xts_ctx->pcc.block, 0, sizeof(xts_ctx->pcc.block));
-	memset(xts_ctx->pcc.bit, 0, sizeof(xts_ctx->pcc.bit));
-	memset(xts_ctx->pcc.xts, 0, sizeof(xts_ctx->pcc.xts));
-	memcpy(xts_ctx->pcc.tweak, walk->iv, sizeof(xts_ctx->pcc.tweak));
-	param = xts_ctx->pcc.key + offset;
-	ret = crypt_s390_pcc(func, param);
+	memset(pcc_param.block, 0, sizeof(pcc_param.block));
+	memset(pcc_param.bit, 0, sizeof(pcc_param.bit));
+	memset(pcc_param.xts, 0, sizeof(pcc_param.xts));
+	memcpy(pcc_param.tweak, walk->iv, sizeof(pcc_param.tweak));
+	memcpy(pcc_param.key, xts_ctx->pcc_key, 32);
+	ret = crypt_s390_pcc(func, &pcc_param.key[offset]);
 	if (ret < 0)
 		return -EIO;
 
-	memcpy(xts_ctx->xts_param, xts_ctx->pcc.xts, 16);
-	param = xts_ctx->key + offset;
+	memcpy(xts_param.key, xts_ctx->key, 32);
+	memcpy(xts_param.init, pcc_param.xts, 16);
 	do {
 		/* only use complete blocks */
 		n = nbytes & ~(AES_BLOCK_SIZE - 1);
 		out = walk->dst.virt.addr;
 		in = walk->src.virt.addr;
 
-		ret = crypt_s390_km(func, param, out, in, n);
+		ret = crypt_s390_km(func, &xts_param.key[offset], out, in, n);
 		if (ret < 0 || ret != n)
 			return -EIO;
 
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 5c477260294f..d5cf85057d63 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -31,6 +31,9 @@ ifeq ($(CONFIG_X86_32),y)
 
         KBUILD_CFLAGS += -msoft-float -mregparm=3 -freg-struct-return
 
+        # Don't autogenerate SSE instructions
+	KBUILD_CFLAGS += -mno-sse
+
         # Never want PIC in a 32-bit kernel, prevent breakage with GCC built
         # with nonstandard options
         KBUILD_CFLAGS += -fno-pic
@@ -57,8 +60,11 @@ else
         KBUILD_AFLAGS += -m64
         KBUILD_CFLAGS += -m64
 
+        # Don't autogenerate SSE instructions
+	KBUILD_CFLAGS += -mno-sse
+
 	# Use -mpreferred-stack-boundary=3 if supported.
-	KBUILD_CFLAGS += $(call cc-option,-mno-sse -mpreferred-stack-boundary=3)
+	KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3)
 
         # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu)
         cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8)
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 4e595ee8c915..749afadfbb33 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -399,9 +399,9 @@ static inline uint64_t blkg_stat_read(struct blkg_stat *stat)
 	uint64_t v;
 
 	do {
-		start = u64_stats_fetch_begin(&stat->syncp);
+		start = u64_stats_fetch_begin_bh(&stat->syncp);
 		v = stat->cnt;
-	} while (u64_stats_fetch_retry(&stat->syncp, start));
+	} while (u64_stats_fetch_retry_bh(&stat->syncp, start));
 
 	return v;
 }
@@ -467,9 +467,9 @@ static inline struct blkg_rwstat blkg_rwstat_read(struct blkg_rwstat *rwstat)
 	struct blkg_rwstat tmp;
 
 	do {
-		start = u64_stats_fetch_begin(&rwstat->syncp);
+		start = u64_stats_fetch_begin_bh(&rwstat->syncp);
 		tmp = *rwstat;
-	} while (u64_stats_fetch_retry(&rwstat->syncp, start));
+	} while (u64_stats_fetch_retry_bh(&rwstat->syncp, start));
 
 	return tmp;
 }
diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 850246206b12..585c3b279feb 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -114,6 +114,9 @@ static ssize_t hash_sendpage(struct socket *sock, struct page *page,
 	struct hash_ctx *ctx = ask->private;
 	int err;
 
+	if (flags & MSG_SENDPAGE_NOTLAST)
+		flags |= MSG_MORE;
+
 	if (flags & MSG_SENDPAGE_NOTLAST)
 		flags |= MSG_MORE;
 
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index a19c027b29bd..918a3b4148b8 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -378,6 +378,9 @@ static ssize_t skcipher_sendpage(struct socket *sock, struct page *page,
 	struct skcipher_sg_list *sgl;
 	int err = -EINVAL;
 
+	if (flags & MSG_SENDPAGE_NOTLAST)
+		flags |= MSG_MORE;
+
 	if (flags & MSG_SENDPAGE_NOTLAST)
 		flags |= MSG_MORE;
 
diff --git a/crypto/authenc.c b/crypto/authenc.c
index ffce19de05cf..528b00bc4769 100644
--- a/crypto/authenc.c
+++ b/crypto/authenc.c
@@ -368,9 +368,10 @@ static void crypto_authenc_encrypt_done(struct crypto_async_request *req,
 	if (!err) {
 		struct crypto_aead *authenc = crypto_aead_reqtfm(areq);
 		struct crypto_authenc_ctx *ctx = crypto_aead_ctx(authenc);
-		struct ablkcipher_request *abreq = aead_request_ctx(areq);
-		u8 *iv = (u8 *)(abreq + 1) +
-			 crypto_ablkcipher_reqsize(ctx->enc);
+		struct authenc_request_ctx *areq_ctx = aead_request_ctx(areq);
+		struct ablkcipher_request *abreq = (void *)(areq_ctx->tail
+							    + ctx->reqoff);
+		u8 *iv = (u8 *)abreq - crypto_ablkcipher_ivsize(ctx->enc);
 
 		err = crypto_authenc_genicv(areq, iv, 0);
 	}
diff --git a/crypto/ccm.c b/crypto/ccm.c
index 499c91717d93..ed009b77e67d 100644
--- a/crypto/ccm.c
+++ b/crypto/ccm.c
@@ -271,7 +271,8 @@ static int crypto_ccm_auth(struct aead_request *req, struct scatterlist *plain,
 	}
 
 	/* compute plaintext into mac */
-	get_data_to_compute(cipher, pctx, plain, cryptlen);
+	if (cryptlen)
+		get_data_to_compute(cipher, pctx, plain, cryptlen);
 
 out:
 	return err;
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 0101af541436..4abdbdff6943 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -3614,6 +3614,7 @@ int ata_scsi_add_hosts(struct ata_host *host, struct scsi_host_template *sht)
 		shost->max_lun = 1;
 		shost->max_channel = 1;
 		shost->max_cmd_len = 16;
+		shost->no_write_same = 1;
 
 		/* Schedule policy is determined by ->qc_defer()
 		 * callback and it needs to see every deferred qc.
diff --git a/drivers/char/i8k.c b/drivers/char/i8k.c
index 40cc0cf2ded6..e6939e13e338 100644
--- a/drivers/char/i8k.c
+++ b/drivers/char/i8k.c
@@ -664,6 +664,13 @@ static struct dmi_system_id __initdata i8k_dmi_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Vostro"),
 		},
 	},
+	{
+		.ident = "Dell XPS421",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "XPS L421X"),
+		},
+	},
         { }
 };
 
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index e86900b03c8e..9e1f7d9b52b5 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -229,7 +229,7 @@ source "drivers/cpufreq/Kconfig.x86"
 endmenu
 
 menu "ARM CPU frequency scaling drivers"
-depends on ARM
+depends on ARM || ARM64
 source "drivers/cpufreq/Kconfig.arm"
 endmenu
 
diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c
index 47674b913843..c8e3b2c48369 100644
--- a/drivers/firewire/sbp2.c
+++ b/drivers/firewire/sbp2.c
@@ -1626,6 +1626,7 @@ static struct scsi_host_template scsi_driver_template = {
 	.cmd_per_lun		= 1,
 	.can_queue		= 1,
 	.sdev_attrs		= sbp2_scsi_sysfs_attrs,
+	.no_write_same		= 1,
 };
 
 MODULE_AUTHOR("Kristian Hoegsberg <krh@bitplanet.net>");
diff --git a/drivers/gpio/gpio-mpc8xxx.c b/drivers/gpio/gpio-mpc8xxx.c
index a0b33a216d4a..2aa3ca215bd6 100644
--- a/drivers/gpio/gpio-mpc8xxx.c
+++ b/drivers/gpio/gpio-mpc8xxx.c
@@ -69,10 +69,14 @@ static int mpc8572_gpio_get(struct gpio_chip *gc, unsigned int gpio)
 	u32 val;
 	struct of_mm_gpio_chip *mm = to_of_mm_gpio_chip(gc);
 	struct mpc8xxx_gpio_chip *mpc8xxx_gc = to_mpc8xxx_gpio_chip(mm);
+	u32 out_mask, out_shadow;
 
-	val = in_be32(mm->regs + GPIO_DAT) & ~in_be32(mm->regs + GPIO_DIR);
+	out_mask = in_be32(mm->regs + GPIO_DIR);
 
-	return (val | mpc8xxx_gc->data) & mpc8xxx_gpio2mask(gpio);
+	val = in_be32(mm->regs + GPIO_DAT) & ~out_mask;
+	out_shadow = mpc8xxx_gc->data & out_mask;
+
+	return (val | out_shadow) & mpc8xxx_gpio2mask(gpio);
 }
 
 static int mpc8xxx_gpio_get(struct gpio_chip *gc, unsigned int gpio)
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 799dbec2646b..a1e431f830e3 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -786,6 +786,8 @@
 #define USB_DEVICE_ID_SYNAPTICS_COMP_TP	0x0009
 #define USB_DEVICE_ID_SYNAPTICS_WTP	0x0010
 #define USB_DEVICE_ID_SYNAPTICS_DPAD	0x0013
+#define USB_DEVICE_ID_SYNAPTICS_LTS1	0x0af8
+#define USB_DEVICE_ID_SYNAPTICS_LTS2	0x1d10
 
 #define USB_VENDOR_ID_THINGM		0x27b8
 #define USB_DEVICE_ID_BLINK1		0x01ed
@@ -913,4 +915,7 @@
 #define USB_VENDOR_ID_PRIMAX	0x0461
 #define USB_DEVICE_ID_PRIMAX_KEYBOARD	0x4e05
 
+#define USB_VENDOR_ID_SIS	0x0457
+#define USB_DEVICE_ID_SIS_TS	0x1013
+
 #endif
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index ae5c63478b92..0db9a67278ba 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -112,6 +112,9 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_DUOSENSE, HID_QUIRK_NO_INIT_REPORTS },
+	{ USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_LTS1, HID_QUIRK_NO_INIT_REPORTS },
+	{ USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_LTS2, HID_QUIRK_NO_INIT_REPORTS },
+	{ USB_VENDOR_ID_SIS, USB_DEVICE_ID_SIS_TS, HID_QUIRK_NO_INIT_REPORTS },
 
 	{ 0, 0 }
 };
diff --git a/drivers/input/Kconfig b/drivers/input/Kconfig
index 3ad49c1f0a30..9c13b63ef915 100644
--- a/drivers/input/Kconfig
+++ b/drivers/input/Kconfig
@@ -80,7 +80,7 @@ config INPUT_MATRIXKMAP
 comment "Userland interfaces"
 
 config INPUT_MOUSEDEV
-	tristate "Mouse interface" if EXPERT
+	tristate "Mouse interface"
 	default y
 	help
 	  Say Y here if you want your mouse to be accessible as char devices
diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig
index 7ac9c9818d55..292f3240e67b 100644
--- a/drivers/input/keyboard/Kconfig
+++ b/drivers/input/keyboard/Kconfig
@@ -2,7 +2,7 @@
 # Input core configuration
 #
 menuconfig INPUT_KEYBOARD
-	bool "Keyboards" if EXPERT || !X86
+	bool "Keyboards"
 	default y
 	help
 	  Say Y here, and a list of supported keyboards will be displayed.
@@ -67,7 +67,7 @@ config KEYBOARD_ATARI
 	  module will be called atakbd.
 
 config KEYBOARD_ATKBD
-	tristate "AT keyboard" if EXPERT || !X86
+	tristate "AT keyboard"
 	default y
 	select SERIO
 	select SERIO_LIBPS2
diff --git a/drivers/input/serio/Kconfig b/drivers/input/serio/Kconfig
index 1bda828f4b55..0455a2735fb0 100644
--- a/drivers/input/serio/Kconfig
+++ b/drivers/input/serio/Kconfig
@@ -2,7 +2,7 @@
 # Input core configuration
 #
 config SERIO
-	tristate "Serial I/O support" if EXPERT || !X86
+	tristate "Serial I/O support"
 	default y
 	help
 	  Say Yes here if you have any input device that uses serial I/O to
@@ -19,7 +19,7 @@ config SERIO
 if SERIO
 
 config SERIO_I8042
-	tristate "i8042 PC Keyboard controller" if EXPERT || !X86
+	tristate "i8042 PC Keyboard controller"
 	default y
 	depends on !PARISC && (!ARM || ARCH_SHARK || FOOTBRIDGE_HOST) && \
 		   (!SUPERH || SH_CAYMAN) && !M68K && !BLACKFIN && !S390
@@ -169,7 +169,7 @@ config SERIO_MACEPS2
 	  module will be called maceps2.
 
 config SERIO_LIBPS2
-	tristate "PS/2 driver library" if EXPERT
+	tristate "PS/2 driver library"
 	depends on SERIO_I8042 || SERIO_I8042=n
 	help
 	  Say Y here if you are using a driver for device connected
diff --git a/drivers/misc/enclosure.c b/drivers/misc/enclosure.c
index 00e5fcac8fdf..cbee842f8b6b 100644
--- a/drivers/misc/enclosure.c
+++ b/drivers/misc/enclosure.c
@@ -198,6 +198,13 @@ static void enclosure_remove_links(struct enclosure_component *cdev)
 {
 	char name[ENCLOSURE_NAME_SIZE];
 
+	/*
+	 * In odd circumstances, like multipath devices, something else may
+	 * already have removed the links, so check for this condition first.
+	 */
+	if (!cdev->dev->kobj.sd)
+		return;
+
 	enclosure_link_name(cdev, name);
 	sysfs_remove_link(&cdev->dev->kobj, name);
 	sysfs_remove_link(&cdev->cdev.kobj, "device");
diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h
index 6a203b6e8346..66f411a6e8ea 100644
--- a/drivers/misc/mei/hw-me-regs.h
+++ b/drivers/misc/mei/hw-me-regs.h
@@ -109,8 +109,12 @@
 #define MEI_DEV_ID_PPT_2      0x1CBA  /* Panther Point */
 #define MEI_DEV_ID_PPT_3      0x1DBA  /* Panther Point */
 
-#define MEI_DEV_ID_LPT        0x8C3A  /* Lynx Point */
+#define MEI_DEV_ID_LPT_H      0x8C3A  /* Lynx Point H */
+#define MEI_DEV_ID_LPT_W      0x8D3A  /* Lynx Point - Wellsburg */
 #define MEI_DEV_ID_LPT_LP     0x9C3A  /* Lynx Point LP */
+#define MEI_DEV_ID_LPT_HR     0x8CBA  /* Lynx Point H Refresh */
+
+#define MEI_DEV_ID_WPT_LP     0x9CBA  /* Wildcat Point LP */
 /*
  * MEI HW Section
  */
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index 0f268329bd3a..371c65ae6be6 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -79,8 +79,11 @@ static DEFINE_PCI_DEVICE_TABLE(mei_me_pci_tbl) = {
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_PPT_1)},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_PPT_2)},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_PPT_3)},
-	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_LPT)},
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_LPT_H)},
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_LPT_W)},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_LPT_LP)},
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_LPT_HR)},
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_WPT_LP)},
 
 	/* required last entry */
 	{0, }
diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c
index e3fc07cf2f62..e59c42b446a9 100644
--- a/drivers/net/can/c_can/c_can.c
+++ b/drivers/net/can/c_can/c_can.c
@@ -712,22 +712,31 @@ static int c_can_set_mode(struct net_device *dev, enum can_mode mode)
 	return 0;
 }
 
-static int c_can_get_berr_counter(const struct net_device *dev,
-					struct can_berr_counter *bec)
+static int __c_can_get_berr_counter(const struct net_device *dev,
+				    struct can_berr_counter *bec)
 {
 	unsigned int reg_err_counter;
 	struct c_can_priv *priv = netdev_priv(dev);
 
-	c_can_pm_runtime_get_sync(priv);
-
 	reg_err_counter = priv->read_reg(priv, C_CAN_ERR_CNT_REG);
 	bec->rxerr = (reg_err_counter & ERR_CNT_REC_MASK) >>
 				ERR_CNT_REC_SHIFT;
 	bec->txerr = reg_err_counter & ERR_CNT_TEC_MASK;
 
+	return 0;
+}
+
+static int c_can_get_berr_counter(const struct net_device *dev,
+				  struct can_berr_counter *bec)
+{
+	struct c_can_priv *priv = netdev_priv(dev);
+	int err;
+
+	c_can_pm_runtime_get_sync(priv);
+	err = __c_can_get_berr_counter(dev, bec);
 	c_can_pm_runtime_put_sync(priv);
 
-	return 0;
+	return err;
 }
 
 /*
@@ -872,7 +881,7 @@ static int c_can_handle_state_change(struct net_device *dev,
 	if (unlikely(!skb))
 		return 0;
 
-	c_can_get_berr_counter(dev, &bec);
+	__c_can_get_berr_counter(dev, &bec);
 	reg_err_counter = priv->read_reg(priv, C_CAN_ERR_CNT_REG);
 	rx_err_passive = (reg_err_counter & ERR_CNT_RP_MASK) >>
 				ERR_CNT_RP_SHIFT;
diff --git a/drivers/net/can/sja1000/sja1000.c b/drivers/net/can/sja1000/sja1000.c
index 7164a999f50f..f17c3018b7c7 100644
--- a/drivers/net/can/sja1000/sja1000.c
+++ b/drivers/net/can/sja1000/sja1000.c
@@ -494,20 +494,20 @@ irqreturn_t sja1000_interrupt(int irq, void *dev_id)
 	uint8_t isrc, status;
 	int n = 0;
 
-	/* Shared interrupts and IRQ off? */
-	if (priv->read_reg(priv, SJA1000_IER) == IRQ_OFF)
-		return IRQ_NONE;
-
 	if (priv->pre_irq)
 		priv->pre_irq(priv);
 
+	/* Shared interrupts and IRQ off? */
+	if (priv->read_reg(priv, SJA1000_IER) == IRQ_OFF)
+		goto out;
+
 	while ((isrc = priv->read_reg(priv, SJA1000_IR)) &&
 	       (n < SJA1000_MAX_IRQ)) {
-		n++;
+
 		status = priv->read_reg(priv, SJA1000_SR);
 		/* check for absent controller due to hw unplug */
 		if (status == 0xFF && sja1000_is_absent(priv))
-			return IRQ_NONE;
+			goto out;
 
 		if (isrc & IRQ_WUI)
 			netdev_warn(dev, "wakeup interrupt\n");
@@ -535,7 +535,7 @@ irqreturn_t sja1000_interrupt(int irq, void *dev_id)
 				status = priv->read_reg(priv, SJA1000_SR);
 				/* check for absent controller */
 				if (status == 0xFF && sja1000_is_absent(priv))
-					return IRQ_NONE;
+					goto out;
 			}
 		}
 		if (isrc & (IRQ_DOI | IRQ_EI | IRQ_BEI | IRQ_EPI | IRQ_ALI)) {
@@ -543,8 +543,9 @@ irqreturn_t sja1000_interrupt(int irq, void *dev_id)
 			if (sja1000_err(dev, isrc, status))
 				break;
 		}
+		n++;
 	}
-
+out:
 	if (priv->post_irq)
 		priv->post_irq(priv);
 
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 0877a052e3ee..b51560d56590 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -6722,12 +6722,6 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget)
 			pci_unmap_single(tp->pdev, dma_addr, skb_size,
 					 PCI_DMA_FROMDEVICE);
 
-			skb = build_skb(data, frag_size);
-			if (!skb) {
-				tg3_frag_free(frag_size != 0, data);
-				goto drop_it_no_recycle;
-			}
-			skb_reserve(skb, TG3_RX_OFFSET(tp));
 			/* Ensure that the update to the data happens
 			 * after the usage of the old DMA mapping.
 			 */
@@ -6735,6 +6729,12 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget)
 
 			ri->data = NULL;
 
+			skb = build_skb(data, frag_size);
+			if (!skb) {
+				tg3_frag_free(frag_size != 0, data);
+				goto drop_it_no_recycle;
+			}
+			skb_reserve(skb, TG3_RX_OFFSET(tp));
 		} else {
 			tg3_recycle_rx(tnapi, tpr, opaque_key,
 				       desc_idx, *post_ptr);
diff --git a/drivers/net/ethernet/smsc/smc91x.h b/drivers/net/ethernet/smsc/smc91x.h
index 370e13dde115..fcb94806f4e9 100644
--- a/drivers/net/ethernet/smsc/smc91x.h
+++ b/drivers/net/ethernet/smsc/smc91x.h
@@ -46,7 +46,8 @@
     defined(CONFIG_MACH_LITTLETON) ||\
     defined(CONFIG_MACH_ZYLONITE2) ||\
     defined(CONFIG_ARCH_VIPER) ||\
-    defined(CONFIG_MACH_STARGATE2)
+    defined(CONFIG_MACH_STARGATE2) ||\
+    defined(CONFIG_ARCH_VERSATILE)
 
 #include <asm/mach-types.h>
 
@@ -154,6 +155,8 @@ static inline void SMC_outw(u16 val, void __iomem *ioaddr, int reg)
 #define SMC_outl(v, a, r)	writel(v, (a) + (r))
 #define SMC_insl(a, r, p, l)	readsl((a) + (r), p, l)
 #define SMC_outsl(a, r, p, l)	writesl((a) + (r), p, l)
+#define SMC_insw(a, r, p, l)	readsw((a) + (r), p, l)
+#define SMC_outsw(a, r, p, l)	writesw((a) + (r), p, l)
 #define SMC_IRQ_FLAGS		(-1)	/* from resource */
 
 /* We actually can't write halfwords properly if not word aligned */
@@ -206,23 +209,6 @@ SMC_outw(u16 val, void __iomem *ioaddr, int reg)
 #define RPC_LSA_DEFAULT		RPC_LED_TX_RX
 #define RPC_LSB_DEFAULT		RPC_LED_100_10
 
-#elif	defined(CONFIG_ARCH_VERSATILE)
-
-#define SMC_CAN_USE_8BIT	1
-#define SMC_CAN_USE_16BIT	1
-#define SMC_CAN_USE_32BIT	1
-#define SMC_NOWAIT		1
-
-#define SMC_inb(a, r)		readb((a) + (r))
-#define SMC_inw(a, r)		readw((a) + (r))
-#define SMC_inl(a, r)		readl((a) + (r))
-#define SMC_outb(v, a, r)	writeb(v, (a) + (r))
-#define SMC_outw(v, a, r)	writew(v, (a) + (r))
-#define SMC_outl(v, a, r)	writel(v, (a) + (r))
-#define SMC_insl(a, r, p, l)	readsl((a) + (r), p, l)
-#define SMC_outsl(a, r, p, l)	writesl((a) + (r), p, l)
-#define SMC_IRQ_FLAGS		(-1)	/* from resource */
-
 #elif defined(CONFIG_MN10300)
 
 /*
diff --git a/drivers/net/wireless/iwlwifi/dvm/tx.c b/drivers/net/wireless/iwlwifi/dvm/tx.c
index a900aaf47790..20e65d3cc3bd 100644
--- a/drivers/net/wireless/iwlwifi/dvm/tx.c
+++ b/drivers/net/wireless/iwlwifi/dvm/tx.c
@@ -445,27 +445,19 @@ int iwlagn_tx_skb(struct iwl_priv *priv,
 	/* Copy MAC header from skb into command buffer */
 	memcpy(tx_cmd->hdr, hdr, hdr_len);
 
+	txq_id = info->hw_queue;
+
 	if (is_agg)
 		txq_id = priv->tid_data[sta_id][tid].agg.txq_id;
 	else if (info->flags & IEEE80211_TX_CTL_SEND_AFTER_DTIM) {
-		/*
-		 * Send this frame after DTIM -- there's a special queue
-		 * reserved for this for contexts that support AP mode.
-		 */
-		txq_id = ctx->mcast_queue;
-
 		/*
 		 * The microcode will clear the more data
 		 * bit in the last frame it transmits.
 		 */
 		hdr->frame_control |=
 			cpu_to_le16(IEEE80211_FCTL_MOREDATA);
-	} else if (info->flags & IEEE80211_TX_CTL_TX_OFFCHAN)
-		txq_id = IWL_AUX_QUEUE;
-	else
-		txq_id = ctx->ac_to_queue[skb_get_queue_mapping(skb)];
+	}
 
-	WARN_ON_ONCE(!is_agg && txq_id != info->hw_queue);
 	WARN_ON_ONCE(is_agg &&
 		     priv->queue_to_mac80211[txq_id] != info->hw_queue);
 
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 1d10b4ec6814..f24dca92ea43 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -18,6 +18,7 @@
  *      2 of the License, or (at your option) any later version.
  */
 #include <linux/ctype.h>
+#include <linux/cpu.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/spinlock.h>
@@ -230,6 +231,100 @@ const void *of_get_property(const struct device_node *np, const char *name,
 }
 EXPORT_SYMBOL(of_get_property);
 
+/*
+ * arch_match_cpu_phys_id - Match the given logical CPU and physical id
+ *
+ * @cpu: logical cpu index of a core/thread
+ * @phys_id: physical identifier of a core/thread
+ *
+ * CPU logical to physical index mapping is architecture specific.
+ * However this __weak function provides a default match of physical
+ * id to logical cpu index. phys_id provided here is usually values read
+ * from the device tree which must match the hardware internal registers.
+ *
+ * Returns true if the physical identifier and the logical cpu index
+ * correspond to the same core/thread, false otherwise.
+ */
+bool __weak arch_match_cpu_phys_id(int cpu, u64 phys_id)
+{
+	return (u32)phys_id == cpu;
+}
+
+/**
+ * Checks if the given "prop_name" property holds the physical id of the
+ * core/thread corresponding to the logical cpu 'cpu'. If 'thread' is not
+ * NULL, local thread number within the core is returned in it.
+ */
+static bool __of_find_n_match_cpu_property(struct device_node *cpun,
+			const char *prop_name, int cpu, unsigned int *thread)
+{
+	const __be32 *cell;
+	int ac, prop_len, tid;
+	u64 hwid;
+
+	ac = of_n_addr_cells(cpun);
+	cell = of_get_property(cpun, prop_name, &prop_len);
+	if (!cell)
+		return false;
+	prop_len /= sizeof(*cell);
+	for (tid = 0; tid < prop_len; tid++) {
+		hwid = of_read_number(cell, ac);
+		if (arch_match_cpu_phys_id(cpu, hwid)) {
+			if (thread)
+				*thread = tid;
+			return true;
+		}
+		cell += ac;
+	}
+	return false;
+}
+
+/**
+ * of_get_cpu_node - Get device node associated with the given logical CPU
+ *
+ * @cpu: CPU number(logical index) for which device node is required
+ * @thread: if not NULL, local thread number within the physical core is
+ *          returned
+ *
+ * The main purpose of this function is to retrieve the device node for the
+ * given logical CPU index. It should be used to initialize the of_node in
+ * cpu device. Once of_node in cpu device is populated, all the further
+ * references can use that instead.
+ *
+ * CPU logical to physical index mapping is architecture specific and is built
+ * before booting secondary cores. This function uses arch_match_cpu_phys_id
+ * which can be overridden by architecture specific implementation.
+ *
+ * Returns a node pointer for the logical cpu if found, else NULL.
+ */
+struct device_node *of_get_cpu_node(int cpu, unsigned int *thread)
+{
+	struct device_node *cpun, *cpus;
+
+	cpus = of_find_node_by_path("/cpus");
+	if (!cpus) {
+		pr_warn("Missing cpus node, bailing out\n");
+		return NULL;
+	}
+
+	for_each_child_of_node(cpus, cpun) {
+		if (of_node_cmp(cpun->type, "cpu"))
+			continue;
+		/* Check for non-standard "ibm,ppc-interrupt-server#s" property
+		 * for thread ids on PowerPC. If it doesn't exist fallback to
+		 * standard "reg" property.
+		 */
+		if (IS_ENABLED(CONFIG_PPC) &&
+			__of_find_n_match_cpu_property(cpun,
+				"ibm,ppc-interrupt-server#s", cpu, thread))
+			return cpun;
+		if (__of_find_n_match_cpu_property(cpun, "reg", cpu, thread))
+			return cpun;
+	}
+	return NULL;
+}
+EXPORT_SYMBOL(of_get_cpu_node);
+
 /** Checks if the given "compat" string matches one of the strings in
  * the device's "compatible" property
  */
diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c
index 5e1e12c0cf42..0a7325361d29 100644
--- a/drivers/scsi/3w-9xxx.c
+++ b/drivers/scsi/3w-9xxx.c
@@ -2025,7 +2025,8 @@ static struct scsi_host_template driver_template = {
 	.cmd_per_lun		= TW_MAX_CMDS_PER_LUN,
 	.use_clustering		= ENABLE_CLUSTERING,
 	.shost_attrs		= twa_host_attrs,
-	.emulated		= 1
+	.emulated		= 1,
+	.no_write_same		= 1,
 };
 
 /* This function will probe and initialize a card */
diff --git a/drivers/scsi/3w-sas.c b/drivers/scsi/3w-sas.c
index c845bdbeb6c0..4de346017e9f 100644
--- a/drivers/scsi/3w-sas.c
+++ b/drivers/scsi/3w-sas.c
@@ -1600,7 +1600,8 @@ static struct scsi_host_template driver_template = {
 	.cmd_per_lun		= TW_MAX_CMDS_PER_LUN,
 	.use_clustering		= ENABLE_CLUSTERING,
 	.shost_attrs		= twl_host_attrs,
-	.emulated		= 1
+	.emulated		= 1,
+	.no_write_same		= 1,
 };
 
 /* This function will probe and initialize a card */
diff --git a/drivers/scsi/3w-xxxx.c b/drivers/scsi/3w-xxxx.c
index 56662ae03dea..430ee3774c3b 100644
--- a/drivers/scsi/3w-xxxx.c
+++ b/drivers/scsi/3w-xxxx.c
@@ -2277,7 +2277,8 @@ static struct scsi_host_template driver_template = {
 	.cmd_per_lun		= TW_MAX_CMDS_PER_LUN,	
 	.use_clustering		= ENABLE_CLUSTERING,
 	.shost_attrs		= tw_host_attrs,
-	.emulated		= 1
+	.emulated		= 1,
+	.no_write_same		= 1,
 };
 
 /* This function will probe and initialize a card */
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index f0d432c139d0..4921ed19a027 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -1081,6 +1081,7 @@ static struct scsi_host_template aac_driver_template = {
 #endif
 	.use_clustering			= ENABLE_CLUSTERING,
 	.emulated			= 1,
+	.no_write_same			= 1,
 };
 
 static void __aac_shutdown(struct aac_dev * aac)
diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c
index 33c52bc2c7b4..278c9fa62067 100644
--- a/drivers/scsi/arcmsr/arcmsr_hba.c
+++ b/drivers/scsi/arcmsr/arcmsr_hba.c
@@ -137,6 +137,7 @@ static struct scsi_host_template arcmsr_scsi_host_template = {
 	.cmd_per_lun		= ARCMSR_MAX_CMD_PERLUN,
 	.use_clustering		= ENABLE_CLUSTERING,
 	.shost_attrs		= arcmsr_host_attrs,
+	.no_write_same		= 1,
 };
 static struct pci_device_id arcmsr_device_id_table[] = {
 	{PCI_DEVICE(PCI_VENDOR_ID_ARECA, PCI_DEVICE_ID_ARECA_1110)},
diff --git a/drivers/scsi/bfa/bfa_fcs.h b/drivers/scsi/bfa/bfa_fcs.h
index a449706c6bc0..6c6c7c35ca10 100644
--- a/drivers/scsi/bfa/bfa_fcs.h
+++ b/drivers/scsi/bfa/bfa_fcs.h
@@ -299,6 +299,7 @@ wwn_t bfa_fcs_lport_get_rport(struct bfa_fcs_lport_s *port, wwn_t wwn,
 struct bfa_fcs_lport_s *bfa_fcs_lookup_port(struct bfa_fcs_s *fcs,
 					    u16 vf_id, wwn_t lpwwn);
 
+void bfa_fcs_lport_set_symname(struct bfa_fcs_lport_s *port, char *symname);
 void bfa_fcs_lport_get_info(struct bfa_fcs_lport_s *port,
 			    struct bfa_lport_info_s *port_info);
 void bfa_fcs_lport_get_attr(struct bfa_fcs_lport_s *port,
diff --git a/drivers/scsi/bfa/bfa_fcs_lport.c b/drivers/scsi/bfa/bfa_fcs_lport.c
index 1224d0462a49..2826961c3806 100644
--- a/drivers/scsi/bfa/bfa_fcs_lport.c
+++ b/drivers/scsi/bfa/bfa_fcs_lport.c
@@ -1097,6 +1097,17 @@ bfa_fcs_lport_init(struct bfa_fcs_lport_s *lport,
 	bfa_sm_send_event(lport, BFA_FCS_PORT_SM_CREATE);
 }
 
+void
+bfa_fcs_lport_set_symname(struct bfa_fcs_lport_s *port,
+				char *symname)
+{
+	strcpy(port->port_cfg.sym_name.symname, symname);
+
+	if (bfa_sm_cmp_state(port, bfa_fcs_lport_sm_online))
+		bfa_fcs_lport_ns_util_send_rspn_id(
+			BFA_FCS_GET_NS_FROM_PORT(port), NULL);
+}
+
 /*
  *  fcs_lport_api
  */
@@ -4950,9 +4961,6 @@ bfa_fcs_lport_ns_util_send_rspn_id(void *cbarg, struct bfa_fcxp_s *fcxp_alloced)
 	u8 *psymbl = &symbl[0];
 	int len;
 
-	if (!bfa_sm_cmp_state(port, bfa_fcs_lport_sm_online))
-		return;
-
 	/* Avoid sending RSPN in the following states. */
 	if (bfa_sm_cmp_state(ns, bfa_fcs_lport_ns_sm_offline) ||
 	    bfa_sm_cmp_state(ns, bfa_fcs_lport_ns_sm_plogi_sending) ||
diff --git a/drivers/scsi/bfa/bfad_attr.c b/drivers/scsi/bfa/bfad_attr.c
index 72f5dc32cc12..58eeca2bbb4b 100644
--- a/drivers/scsi/bfa/bfad_attr.c
+++ b/drivers/scsi/bfa/bfad_attr.c
@@ -610,11 +610,8 @@ bfad_im_vport_set_symbolic_name(struct fc_vport *fc_vport)
 		return;
 
 	spin_lock_irqsave(&bfad->bfad_lock, flags);
-	if (strlen(sym_name) > 0) {
-		strcpy(fcs_vport->lport.port_cfg.sym_name.symname, sym_name);
-		bfa_fcs_lport_ns_util_send_rspn_id(
-			BFA_FCS_GET_NS_FROM_PORT((&fcs_vport->lport)), NULL);
-	}
+	if (strlen(sym_name) > 0)
+		bfa_fcs_lport_set_symname(&fcs_vport->lport, sym_name);
 	spin_unlock_irqrestore(&bfad->bfad_lock, flags);
 }
 
diff --git a/drivers/scsi/gdth.c b/drivers/scsi/gdth.c
index 6d55b4e7e792..aec3d4da276f 100644
--- a/drivers/scsi/gdth.c
+++ b/drivers/scsi/gdth.c
@@ -4686,6 +4686,7 @@ static struct scsi_host_template gdth_template = {
         .cmd_per_lun            = GDTH_MAXC_P_L,
         .unchecked_isa_dma      = 1,
         .use_clustering         = ENABLE_CLUSTERING,
+	.no_write_same		= 1,
 };
 
 #ifdef CONFIG_ISA
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index df0c3c71ea43..3cafe0d784b8 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -388,6 +388,7 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
 	shost->unchecked_isa_dma = sht->unchecked_isa_dma;
 	shost->use_clustering = sht->use_clustering;
 	shost->ordered_tag = sht->ordered_tag;
+	shost->no_write_same = sht->no_write_same;
 
 	if (sht->supported_mode == MODE_UNKNOWN)
 		/* means we didn't set it ... default to INITIATOR */
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 7f4f790a3d71..0353d7f2172b 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -538,6 +538,7 @@ static struct scsi_host_template hpsa_driver_template = {
 	.sdev_attrs = hpsa_sdev_attrs,
 	.shost_attrs = hpsa_shost_attrs,
 	.max_sectors = 8192,
+	.no_write_same = 1,
 };
 
 
@@ -1265,7 +1266,7 @@ static void complete_scsi_command(struct CommandList *cp)
 					"has check condition: aborted command: "
 					"ASC: 0x%x, ASCQ: 0x%x\n",
 					cp, asc, ascq);
-				cmd->result = DID_SOFT_ERROR << 16;
+				cmd->result |= DID_SOFT_ERROR << 16;
 				break;
 			}
 			/* Must be some other type of check condition */
@@ -4904,7 +4905,7 @@ static int hpsa_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	hpsa_hba_inquiry(h);
 	hpsa_register_scsi(h);	/* hook ourselves into SCSI subsystem */
 	start_controller_lockup_detector(h);
-	return 1;
+	return 0;
 
 clean4:
 	hpsa_free_sg_chain_blocks(h);
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 6c4cedb44c07..0ff37a5e286c 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -6267,7 +6267,8 @@ static struct scsi_host_template driver_template = {
 	.use_clustering = ENABLE_CLUSTERING,
 	.shost_attrs = ipr_ioa_attrs,
 	.sdev_attrs = ipr_dev_attrs,
-	.proc_name = IPR_NAME
+	.proc_name = IPR_NAME,
+	.no_write_same = 1,
 };
 
 /**
diff --git a/drivers/scsi/ips.c b/drivers/scsi/ips.c
index 8d5ea8a1e5a6..52a216f21ae5 100644
--- a/drivers/scsi/ips.c
+++ b/drivers/scsi/ips.c
@@ -374,6 +374,7 @@ static struct scsi_host_template ips_driver_template = {
 	.sg_tablesize		= IPS_MAX_SG,
 	.cmd_per_lun		= 3,
 	.use_clustering		= ENABLE_CLUSTERING,
+	.no_write_same		= 1,
 };
 
 
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 161c98efade9..d2895836f9fa 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -211,7 +211,7 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
 		qc->tf.nsect = 0;
 	}
 
-	ata_tf_to_fis(&qc->tf, 1, 0, (u8*)&task->ata_task.fis);
+	ata_tf_to_fis(&qc->tf, qc->dev->link->pmp, 1, (u8 *)&task->ata_task.fis);
 	task->uldd_task = qc;
 	if (ata_is_atapi(qc->tf.protocol)) {
 		memcpy(task->ata_task.atapi_packet, qc->cdb, qc->dev->cdb_len);
diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c
index 846f475f62c1..60cf7b1f5423 100644
--- a/drivers/scsi/megaraid.c
+++ b/drivers/scsi/megaraid.c
@@ -4244,6 +4244,7 @@ static struct scsi_host_template megaraid_template = {
 	.eh_device_reset_handler	= megaraid_reset,
 	.eh_bus_reset_handler		= megaraid_reset,
 	.eh_host_reset_handler		= megaraid_reset,
+	.no_write_same			= 1,
 };
 
 static int
diff --git a/drivers/scsi/megaraid/megaraid_mbox.c b/drivers/scsi/megaraid/megaraid_mbox.c
index e6a1e0b38a19..3316d8031e82 100644
--- a/drivers/scsi/megaraid/megaraid_mbox.c
+++ b/drivers/scsi/megaraid/megaraid_mbox.c
@@ -367,6 +367,7 @@ static struct scsi_host_template megaraid_template_g = {
 	.eh_host_reset_handler		= megaraid_reset_handler,
 	.change_queue_depth		= megaraid_change_queue_depth,
 	.use_clustering			= ENABLE_CLUSTERING,
+	.no_write_same			= 1,
 	.sdev_attrs			= megaraid_sdev_attrs,
 	.shost_attrs			= megaraid_shost_attrs,
 };
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 9b60dc129a53..b3e5c1787876 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -2099,6 +2099,7 @@ static struct scsi_host_template megasas_template = {
 	.bios_param = megasas_bios_param,
 	.use_clustering = ENABLE_CLUSTERING,
 	.change_queue_depth = megasas_change_queue_depth,
+	.no_write_same = 1,
 };
 
 /**
diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c
index 8e1b73775065..bfb72ec277c7 100644
--- a/drivers/scsi/pmcraid.c
+++ b/drivers/scsi/pmcraid.c
@@ -4314,6 +4314,7 @@ static struct scsi_host_template pmcraid_host_template = {
 	.this_id = -1,
 	.sg_tablesize = PMCRAID_MAX_IOADLS,
 	.max_sectors = PMCRAID_IOA_MAX_SECTORS,
+	.no_write_same = 1,
 	.cmd_per_lun = PMCRAID_MAX_CMD_PER_LUN,
 	.use_clustering = ENABLE_CLUSTERING,
 	.shost_attrs = pmcraid_host_attrs,
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 734a29a70f63..9bc913b92d13 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -2627,6 +2627,12 @@ static void sd_read_write_same(struct scsi_disk *sdkp, unsigned char *buffer)
 {
 	struct scsi_device *sdev = sdkp->device;
 
+	if (sdev->host->no_write_same) {
+		sdev->no_write_same = 1;
+
+		return;
+	}
+
 	if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, INQUIRY) < 0) {
 		sdev->no_report_opcodes = 1;
 
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 16a3a0cc9672..fb7437dd5b7a 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -1454,6 +1454,7 @@ static struct scsi_host_template scsi_driver = {
 	.use_clustering =	DISABLE_CLUSTERING,
 	/* Make sure we dont get a sg segment crosses a page boundary */
 	.dma_boundary =		PAGE_SIZE-1,
+	.no_write_same =	1,
 };
 
 enum {
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 9b1cbcf8fb7f..81f59e8b7521 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1529,6 +1529,8 @@ static int acm_reset_resume(struct usb_interface *intf)
 
 static const struct usb_device_id acm_ids[] = {
 	/* quirky and broken devices */
+	{ USB_DEVICE(0x17ef, 0x7000), /* Lenovo USB modem */
+	.driver_info = NO_UNION_NORMAL, },/* has no union descriptor */
 	{ USB_DEVICE(0x0870, 0x0001), /* Metricom GS Modem */
 	.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
 	},
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index aa3aed5458a6..92549cc4665f 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -2131,6 +2131,20 @@ static void ftdi_set_termios(struct tty_struct *tty,
 		termios->c_cflag |= CRTSCTS;
 	}
 
+	/*
+	 * All FTDI UART chips are limited to CS7/8. We won't pretend to
+	 * support CS5/6 and revert the CSIZE setting instead.
+	 */
+	if ((C_CSIZE(tty) != CS8) && (C_CSIZE(tty) != CS7)) {
+		dev_warn(ddev, "requested CSIZE setting not supported\n");
+
+		termios->c_cflag &= ~CSIZE;
+		if (old_termios)
+			termios->c_cflag |= old_termios->c_cflag & CSIZE;
+		else
+			termios->c_cflag |= CS8;
+	}
+
 	cflag = termios->c_cflag;
 
 	if (!old_termios)
@@ -2167,19 +2181,16 @@ static void ftdi_set_termios(struct tty_struct *tty,
 	} else {
 		urb_value |= FTDI_SIO_SET_DATA_PARITY_NONE;
 	}
-	if (cflag & CSIZE) {
-		switch (cflag & CSIZE) {
-		case CS7:
-			urb_value |= 7;
-			dev_dbg(ddev, "Setting CS7\n");
-			break;
-		case CS8:
-			urb_value |= 8;
-			dev_dbg(ddev, "Setting CS8\n");
-			break;
-		default:
-			dev_err(ddev, "CSIZE was set but not CS7-CS8\n");
-		}
+	switch (cflag & CSIZE) {
+	case CS7:
+		urb_value |= 7;
+		dev_dbg(ddev, "Setting CS7\n");
+		break;
+	default:
+	case CS8:
+		urb_value |= 8;
+		dev_dbg(ddev, "Setting CS8\n");
+		break;
 	}
 
 	/* This is needed by the break command since it uses the same command
diff --git a/drivers/usb/serial/mos7840.c b/drivers/usb/serial/mos7840.c
index 8b3d0abe7e14..d06013033def 100644
--- a/drivers/usb/serial/mos7840.c
+++ b/drivers/usb/serial/mos7840.c
@@ -1875,25 +1875,25 @@ static void mos7840_change_port_settings(struct tty_struct *tty,
 	iflag = tty->termios.c_iflag;
 
 	/* Change the number of bits */
-	if (cflag & CSIZE) {
-		switch (cflag & CSIZE) {
-		case CS5:
-			lData = LCR_BITS_5;
-			break;
+	switch (cflag & CSIZE) {
+	case CS5:
+		lData = LCR_BITS_5;
+		break;
 
-		case CS6:
-			lData = LCR_BITS_6;
-			break;
+	case CS6:
+		lData = LCR_BITS_6;
+		break;
 
-		case CS7:
-			lData = LCR_BITS_7;
-			break;
-		default:
-		case CS8:
-			lData = LCR_BITS_8;
-			break;
-		}
+	case CS7:
+		lData = LCR_BITS_7;
+		break;
+
+	default:
+	case CS8:
+		lData = LCR_BITS_8;
+		break;
 	}
+
 	/* Change the Parity bit */
 	if (cflag & PARENB) {
 		if (cflag & PARODD) {
diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c
index 048cd44d51b1..5e39f5c4941b 100644
--- a/drivers/usb/serial/pl2303.c
+++ b/drivers/usb/serial/pl2303.c
@@ -304,24 +304,22 @@ static void pl2303_set_termios(struct tty_struct *tty,
 	dev_dbg(&port->dev, "0xa1:0x21:0:0  %d - %x %x %x %x %x %x %x\n", i,
 	    buf[0], buf[1], buf[2], buf[3], buf[4], buf[5], buf[6]);
 
-	if (cflag & CSIZE) {
-		switch (cflag & CSIZE) {
-		case CS5:
-			buf[6] = 5;
-			break;
-		case CS6:
-			buf[6] = 6;
-			break;
-		case CS7:
-			buf[6] = 7;
-			break;
-		default:
-		case CS8:
-			buf[6] = 8;
-			break;
-		}
-		dev_dbg(&port->dev, "data bits = %d\n", buf[6]);
+	switch (cflag & CSIZE) {
+	case CS5:
+		buf[6] = 5;
+		break;
+	case CS6:
+		buf[6] = 6;
+		break;
+	case CS7:
+		buf[6] = 7;
+		break;
+	default:
+	case CS8:
+		buf[6] = 8;
+		break;
 	}
+	dev_dbg(&port->dev, "data bits = %d\n", buf[6]);
 
 	/* For reference buf[0]:buf[3] baud rate value */
 	/* NOTE: Only the values defined in baud_sup are supported !
diff --git a/drivers/usb/serial/spcp8x5.c b/drivers/usb/serial/spcp8x5.c
index ddf6c47137dc..1694d4ff1639 100644
--- a/drivers/usb/serial/spcp8x5.c
+++ b/drivers/usb/serial/spcp8x5.c
@@ -346,22 +346,20 @@ static void spcp8x5_set_termios(struct tty_struct *tty,
 	}
 
 	/* Set Data Length : 00:5bit, 01:6bit, 10:7bit, 11:8bit */
-	if (cflag & CSIZE) {
-		switch (cflag & CSIZE) {
-		case CS5:
-			buf[1] |= SET_UART_FORMAT_SIZE_5;
-			break;
-		case CS6:
-			buf[1] |= SET_UART_FORMAT_SIZE_6;
-			break;
-		case CS7:
-			buf[1] |= SET_UART_FORMAT_SIZE_7;
-			break;
-		default:
-		case CS8:
-			buf[1] |= SET_UART_FORMAT_SIZE_8;
-			break;
-		}
+	switch (cflag & CSIZE) {
+	case CS5:
+		buf[1] |= SET_UART_FORMAT_SIZE_5;
+		break;
+	case CS6:
+		buf[1] |= SET_UART_FORMAT_SIZE_6;
+		break;
+	case CS7:
+		buf[1] |= SET_UART_FORMAT_SIZE_7;
+		break;
+	default:
+	case CS8:
+		buf[1] |= SET_UART_FORMAT_SIZE_8;
+		break;
 	}
 
 	/* Set Stop bit2 : 0:1bit 1:2bit */
diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig
index f8c724087168..a3279c7def71 100644
--- a/drivers/video/Kconfig
+++ b/drivers/video/Kconfig
@@ -317,7 +317,8 @@ config FB_PM2_FIFO_DISCONNECT
 
 config FB_ARMCLCD
 	tristate "ARM PrimeCell PL110 support"
-	depends on FB && ARM && ARM_AMBA
+	depends on ARM || ARM64 || COMPILE_TEST
+	depends on FB && ARM_AMBA
 	select FB_CFB_FILLRECT
 	select FB_CFB_COPYAREA
 	select FB_CFB_IMAGEBLIT
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index d5418c1be9aa..840604ed0235 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -920,9 +920,10 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
 		ret = m2p_add_override(mfn, pages[i], kmap_ops ?
 				       &kmap_ops[i] : NULL);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
+ out:
 	if (lazy)
 		arch_leave_lazy_mmu_mode();
 
@@ -953,9 +954,10 @@ int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
 		ret = m2p_remove_override(pages[i], kmap_ops ?
 				       &kmap_ops[i] : NULL);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
+ out:
 	if (lazy)
 		arch_leave_lazy_mmu_mode();
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index b69c70a1e2f3..10a0dde7731a 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -4401,11 +4401,17 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
 		return;
 
 	switch (task->tk_status) {
-	case -NFS4ERR_STALE_STATEID:
-	case -NFS4ERR_EXPIRED:
 	case 0:
 		renew_lease(data->res.server, data->timestamp);
 		break;
+	case -NFS4ERR_ADMIN_REVOKED:
+	case -NFS4ERR_DELEG_REVOKED:
+	case -NFS4ERR_BAD_STATEID:
+	case -NFS4ERR_OLD_STATEID:
+	case -NFS4ERR_STALE_STATEID:
+	case -NFS4ERR_EXPIRED:
+		task->tk_status = 0;
+		break;
 	default:
 		if (nfs4_async_handle_error(task, data->res.server, NULL) ==
 				-EAGAIN) {
diff --git a/fs/pipe.c b/fs/pipe.c
index d2c45e14e6d8..0e0752ef2715 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -726,11 +726,25 @@ pipe_poll(struct file *filp, poll_table *wait)
 	return mask;
 }
 
+static void put_pipe_info(struct inode *inode, struct pipe_inode_info *pipe)
+{
+	int kill = 0;
+
+	spin_lock(&inode->i_lock);
+	if (!--pipe->files) {
+		inode->i_pipe = NULL;
+		kill = 1;
+	}
+	spin_unlock(&inode->i_lock);
+
+	if (kill)
+		free_pipe_info(pipe);
+}
+
 static int
 pipe_release(struct inode *inode, struct file *file)
 {
-	struct pipe_inode_info *pipe = inode->i_pipe;
-	int kill = 0;
+	struct pipe_inode_info *pipe = file->private_data;
 
 	__pipe_lock(pipe);
 	if (file->f_mode & FMODE_READ)
@@ -743,17 +757,9 @@ pipe_release(struct inode *inode, struct file *file)
 		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
 		kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
 	}
-	spin_lock(&inode->i_lock);
-	if (!--pipe->files) {
-		inode->i_pipe = NULL;
-		kill = 1;
-	}
-	spin_unlock(&inode->i_lock);
 	__pipe_unlock(pipe);
 
-	if (kill)
-		free_pipe_info(pipe);
-
+	put_pipe_info(inode, pipe);
 	return 0;
 }
 
@@ -1014,7 +1020,6 @@ static int fifo_open(struct inode *inode, struct file *filp)
 {
 	struct pipe_inode_info *pipe;
 	bool is_pipe = inode->i_sb->s_magic == PIPEFS_MAGIC;
-	int kill = 0;
 	int ret;
 
 	filp->f_version = 0;
@@ -1130,15 +1135,9 @@ static int fifo_open(struct inode *inode, struct file *filp)
 	goto err;
 
 err:
-	spin_lock(&inode->i_lock);
-	if (!--pipe->files) {
-		inode->i_pipe = NULL;
-		kill = 1;
-	}
-	spin_unlock(&inode->i_lock);
 	__pipe_unlock(pipe);
-	if (kill)
-		free_pipe_info(pipe);
+
+	put_pipe_info(inode, pipe);
 	return ret;
 }
 
diff --git a/include/crypto/scatterwalk.h b/include/crypto/scatterwalk.h
index 3744d2a642df..2cddd2b92c19 100644
--- a/include/crypto/scatterwalk.h
+++ b/include/crypto/scatterwalk.h
@@ -36,6 +36,7 @@ static inline void scatterwalk_sg_chain(struct scatterlist *sg1, int num,
 {
 	sg_set_page(&sg1[num - 1], (void *)sg2, 0, 0);
 	sg1[num - 1].page_link &= ~0x02;
+	sg1[num - 1].page_link |= 0x01;
 }
 
 static inline struct scatterlist *scatterwalk_sg_next(struct scatterlist *sg)
@@ -43,7 +44,7 @@ static inline struct scatterlist *scatterwalk_sg_next(struct scatterlist *sg)
 	if (sg_is_last(sg))
 		return NULL;
 
-	return (++sg)->length ? sg : (void *)sg_page(sg);
+	return (++sg)->length ? sg : sg_chain_ptr(sg);
 }
 
 static inline void scatterwalk_crypto_chain(struct scatterlist *head,
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 39d4f9d37901..3bf2bc41e41c 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -29,6 +29,7 @@ struct cpu {
 extern int register_cpu(struct cpu *cpu, int num);
 extern struct device *get_cpu_device(unsigned cpu);
 extern bool cpu_is_hotpluggable(unsigned cpu);
+extern bool arch_match_cpu_phys_id(int cpu, u64 phys_id);
 
 extern int cpu_add_dev_attr(struct device_attribute *attr);
 extern void cpu_remove_dev_attr(struct device_attribute *attr);
diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h
index 661d374aeb2d..f8d41cb1cbe0 100644
--- a/include/linux/genalloc.h
+++ b/include/linux/genalloc.h
@@ -66,8 +66,8 @@ struct gen_pool_chunk {
 	struct list_head next_chunk;	/* next chunk in pool */
 	atomic_t avail;
 	phys_addr_t phys_addr;		/* physical starting address of memory chunk */
-	unsigned long start_addr;	/* starting address of memory chunk */
-	unsigned long end_addr;		/* ending address of memory chunk */
+	unsigned long start_addr;	/* start address of memory chunk */
+	unsigned long end_addr;		/* end address of memory chunk (inclusive) */
 	unsigned long bits[0];		/* bitmap for allocating memory chunk */
 };
 
diff --git a/include/linux/of.h b/include/linux/of.h
index 1fd08ca23106..c0bb2f188048 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -266,6 +266,7 @@ extern int of_device_is_available(const struct device_node *device);
 extern const void *of_get_property(const struct device_node *node,
 				const char *name,
 				int *lenp);
+extern struct device_node *of_get_cpu_node(int cpu, unsigned int *thread);
 #define for_each_property_of_node(dn, pp) \
 	for (pp = dn->properties; pp != NULL; pp = pp->next)
 
@@ -459,6 +460,12 @@ static inline const void *of_get_property(const struct device_node *node,
 	return NULL;
 }
 
+static inline struct device_node *of_get_cpu_node(int cpu,
+					unsigned int *thread)
+{
+	return NULL;
+}
+
 static inline int of_property_read_u64(const struct device_node *np,
 				       const char *propname, u64 *out_value)
 {
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 755243572219..50769a72166b 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -475,6 +475,9 @@ struct scsi_host_template {
 	 */
 	unsigned ordered_tag:1;
 
+	/* True if the controller does not support WRITE SAME */
+	unsigned no_write_same:1;
+
 	/*
 	 * Countdown for host blocking with no commands outstanding.
 	 */
@@ -674,6 +677,9 @@ struct Scsi_Host {
 	/* Don't resume host in EH */
 	unsigned eh_noresume:1;
 
+	/* The controller does not support WRITE SAME */
+	unsigned no_write_same:1;
+
 	/*
 	 * Optional work queue to be utilized by the transport
 	 */
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index fe4b09cf829c..c72b7a43beb9 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -50,7 +50,7 @@ static void resume_irqs(bool want_early)
 		bool is_early = desc->action &&
 			desc->action->flags & IRQF_EARLY_RESUME;
 
-		if (is_early != want_early)
+		if (!is_early && want_early)
 			continue;
 
 		raw_spin_lock_irqsave(&desc->lock, flags);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index fcc261c5df29..1c5b0fcd83b2 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1328,7 +1328,7 @@ static inline void old_vsyscall_fixup(struct timekeeper *tk)
 	tk->xtime_nsec -= remainder;
 	tk->xtime_nsec += 1ULL << tk->shift;
 	tk->ntp_error += remainder << tk->ntp_error_shift;
-
+	tk->ntp_error -= (1ULL << tk->shift) << tk->ntp_error_shift;
 }
 #else
 #define old_vsyscall_fixup(tk)
diff --git a/lib/genalloc.c b/lib/genalloc.c
index b35cfa9bc3d4..2a39bf62d8c1 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -37,6 +37,11 @@
 #include <linux/of_address.h>
 #include <linux/of_device.h>
 
+static inline size_t chunk_size(const struct gen_pool_chunk *chunk)
+{
+	return chunk->end_addr - chunk->start_addr + 1;
+}
+
 static int set_bits_ll(unsigned long *addr, unsigned long mask_to_set)
 {
 	unsigned long val, nval;
@@ -188,7 +193,7 @@ int gen_pool_add_virt(struct gen_pool *pool, unsigned long virt, phys_addr_t phy
 
 	chunk->phys_addr = phys;
 	chunk->start_addr = virt;
-	chunk->end_addr = virt + size;
+	chunk->end_addr = virt + size - 1;
 	atomic_set(&chunk->avail, size);
 
 	spin_lock(&pool->lock);
@@ -213,7 +218,7 @@ phys_addr_t gen_pool_virt_to_phys(struct gen_pool *pool, unsigned long addr)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) {
-		if (addr >= chunk->start_addr && addr < chunk->end_addr) {
+		if (addr >= chunk->start_addr && addr <= chunk->end_addr) {
 			paddr = chunk->phys_addr + (addr - chunk->start_addr);
 			break;
 		}
@@ -242,7 +247,7 @@ void gen_pool_destroy(struct gen_pool *pool)
 		chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk);
 		list_del(&chunk->next_chunk);
 
-		end_bit = (chunk->end_addr - chunk->start_addr) >> order;
+		end_bit = chunk_size(chunk) >> order;
 		bit = find_next_bit(chunk->bits, end_bit, 0);
 		BUG_ON(bit < end_bit);
 
@@ -283,7 +288,7 @@ unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size)
 		if (size > atomic_read(&chunk->avail))
 			continue;
 
-		end_bit = (chunk->end_addr - chunk->start_addr) >> order;
+		end_bit = chunk_size(chunk) >> order;
 retry:
 		start_bit = pool->algo(chunk->bits, end_bit, start_bit, nbits,
 				pool->data);
@@ -330,8 +335,8 @@ void gen_pool_free(struct gen_pool *pool, unsigned long addr, size_t size)
 	nbits = (size + (1UL << order) - 1) >> order;
 	rcu_read_lock();
 	list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) {
-		if (addr >= chunk->start_addr && addr < chunk->end_addr) {
-			BUG_ON(addr + size > chunk->end_addr);
+		if (addr >= chunk->start_addr && addr <= chunk->end_addr) {
+			BUG_ON(addr + size - 1 > chunk->end_addr);
 			start_bit = (addr - chunk->start_addr) >> order;
 			remain = bitmap_clear_ll(chunk->bits, start_bit, nbits);
 			BUG_ON(remain);
@@ -400,7 +405,7 @@ size_t gen_pool_size(struct gen_pool *pool)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk)
-		size += chunk->end_addr - chunk->start_addr;
+		size += chunk_size(chunk);
 	rcu_read_unlock();
 	return size;
 }
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c3075b552248..233f1911dc34 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1070,6 +1070,9 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset,
 	struct udp_sock *up = udp_sk(sk);
 	int ret;
 
+	if (flags & MSG_SENDPAGE_NOTLAST)
+		flags |= MSG_MORE;
+
 	if (flags & MSG_SENDPAGE_NOTLAST)
 		flags |= MSG_MORE;
 
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 661afe7d85e4..937079a5265a 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -1763,6 +1763,7 @@ enum {
 	ALC889_FIXUP_DAC_ROUTE,
 	ALC889_FIXUP_MBP_VREF,
 	ALC889_FIXUP_IMAC91_VREF,
+	ALC889_FIXUP_MBA21_VREF,
 	ALC882_FIXUP_INV_DMIC,
 	ALC882_FIXUP_NO_PRIMARY_HP,
 	ALC887_FIXUP_ASUS_BASS,
@@ -1866,17 +1867,13 @@ static void alc889_fixup_mbp_vref(struct hda_codec *codec,
 	}
 }
 
-/* Set VREF on speaker pins on imac91 */
-static void alc889_fixup_imac91_vref(struct hda_codec *codec,
-				     const struct hda_fixup *fix, int action)
+static void alc889_fixup_mac_pins(struct hda_codec *codec,
+				  const hda_nid_t *nids, int num_nids)
 {
 	struct alc_spec *spec = codec->spec;
-	static hda_nid_t nids[2] = { 0x18, 0x1a };
 	int i;
 
-	if (action != HDA_FIXUP_ACT_INIT)
-		return;
-	for (i = 0; i < ARRAY_SIZE(nids); i++) {
+	for (i = 0; i < num_nids; i++) {
 		unsigned int val;
 		val = snd_hda_codec_get_pin_target(codec, nids[i]);
 		val |= AC_PINCTL_VREF_50;
@@ -1885,6 +1882,26 @@ static void alc889_fixup_imac91_vref(struct hda_codec *codec,
 	spec->gen.keep_vref_in_automute = 1;
 }
 
+/* Set VREF on speaker pins on imac91 */
+static void alc889_fixup_imac91_vref(struct hda_codec *codec,
+				     const struct hda_fixup *fix, int action)
+{
+	static hda_nid_t nids[2] = { 0x18, 0x1a };
+
+	if (action == HDA_FIXUP_ACT_INIT)
+		alc889_fixup_mac_pins(codec, nids, ARRAY_SIZE(nids));
+}
+
+/* Set VREF on speaker pins on mba21 */
+static void alc889_fixup_mba21_vref(struct hda_codec *codec,
+				    const struct hda_fixup *fix, int action)
+{
+	static hda_nid_t nids[2] = { 0x18, 0x19 };
+
+	if (action == HDA_FIXUP_ACT_INIT)
+		alc889_fixup_mac_pins(codec, nids, ARRAY_SIZE(nids));
+}
+
 /* Don't take HP output as primary
  * Strangely, the speaker output doesn't work on Vaio Z and some Vaio
  * all-in-one desktop PCs (for example VGC-LN51JGB) through DAC 0x05
@@ -2079,6 +2096,12 @@ static const struct hda_fixup alc882_fixups[] = {
 		.chained = true,
 		.chain_id = ALC882_FIXUP_GPIO1,
 	},
+	[ALC889_FIXUP_MBA21_VREF] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc889_fixup_mba21_vref,
+		.chained = true,
+		.chain_id = ALC889_FIXUP_MBP_VREF,
+	},
 	[ALC882_FIXUP_INV_DMIC] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_inv_dmic_0x12,
@@ -2143,7 +2166,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x106b, 0x3000, "iMac", ALC889_FIXUP_MBP_VREF),
 	SND_PCI_QUIRK(0x106b, 0x3200, "iMac 7,1 Aluminum", ALC882_FIXUP_EAPD),
 	SND_PCI_QUIRK(0x106b, 0x3400, "MacBookAir 1,1", ALC889_FIXUP_MBP_VREF),
-	SND_PCI_QUIRK(0x106b, 0x3500, "MacBookAir 2,1", ALC889_FIXUP_MBP_VREF),
+	SND_PCI_QUIRK(0x106b, 0x3500, "MacBookAir 2,1", ALC889_FIXUP_MBA21_VREF),
 	SND_PCI_QUIRK(0x106b, 0x3600, "Macbook 3,1", ALC889_FIXUP_MBP_VREF),
 	SND_PCI_QUIRK(0x106b, 0x3800, "MacbookPro 4,1", ALC889_FIXUP_MBP_VREF),
 	SND_PCI_QUIRK(0x106b, 0x3e00, "iMac 24 Aluminum", ALC885_FIXUP_MACPRO_GPIO),
@@ -3041,6 +3064,7 @@ static void alc_headset_mode_ctia(struct hda_codec *codec)
 		alc_write_coef_idx(codec, 0x18, 0x7388);
 		break;
 	case 0x10ec0668:
+		alc_write_coef_idx(codec, 0x11, 0x0001);
 		alc_write_coef_idx(codec, 0x15, 0x0d60);
 		alc_write_coef_idx(codec, 0xc3, 0x0000);
 		break;
@@ -3063,6 +3087,7 @@ static void alc_headset_mode_omtp(struct hda_codec *codec)
 		alc_write_coef_idx(codec, 0x18, 0x7388);
 		break;
 	case 0x10ec0668:
+		alc_write_coef_idx(codec, 0x11, 0x0001);
 		alc_write_coef_idx(codec, 0x15, 0x0d50);
 		alc_write_coef_idx(codec, 0xc3, 0x0000);
 		break;
@@ -3632,6 +3657,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x0613, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0614, "Dell Inspiron 3135", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0616, "Dell Vostro 5470", ALC290_FIXUP_MONO_SPEAKERS),
+	SND_PCI_QUIRK(0x1028, 0x0638, "Dell Inspiron 5439", ALC290_FIXUP_MONO_SPEAKERS),
 	SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),
 	SND_PCI_QUIRK(0x103c, 0x18e6, "HP", ALC269_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x1973, "HP Pavilion", ALC269_FIXUP_HP_MUTE_LED_MIC1),
@@ -3896,6 +3922,7 @@ enum {
 	ALC861_FIXUP_AMP_VREF_0F,
 	ALC861_FIXUP_NO_JACK_DETECT,
 	ALC861_FIXUP_ASUS_A6RP,
+	ALC660_FIXUP_ASUS_W7J,
 };
 
 /* On some laptops, VREF of pin 0x0f is abused for controlling the main amp */
@@ -3945,10 +3972,22 @@ static const struct hda_fixup alc861_fixups[] = {
 		.v.func = alc861_fixup_asus_amp_vref_0f,
 		.chained = true,
 		.chain_id = ALC861_FIXUP_NO_JACK_DETECT,
+	},
+	[ALC660_FIXUP_ASUS_W7J] = {
+		.type = HDA_FIXUP_VERBS,
+		.v.verbs = (const struct hda_verb[]) {
+			/* ASUS W7J needs a magic pin setup on unused NID 0x10
+			 * for enabling outputs
+			 */
+			{0x10, AC_VERB_SET_PIN_WIDGET_CONTROL, 0x24},
+			{ }
+		},
 	}
 };
 
 static const struct snd_pci_quirk alc861_fixup_tbl[] = {
+	SND_PCI_QUIRK(0x1043, 0x1253, "ASUS W7J", ALC660_FIXUP_ASUS_W7J),
+	SND_PCI_QUIRK(0x1043, 0x1263, "ASUS Z35HL", ALC660_FIXUP_ASUS_W7J),
 	SND_PCI_QUIRK(0x1043, 0x1393, "ASUS A6Rp", ALC861_FIXUP_ASUS_A6RP),
 	SND_PCI_QUIRK_VENDOR(0x1043, "ASUS laptop", ALC861_FIXUP_AMP_VREF_0F),
 	SND_PCI_QUIRK(0x1462, 0x7254, "HP DX2200", ALC861_FIXUP_NO_JACK_DETECT),
diff --git a/sound/soc/codecs/wm8731.c b/sound/soc/codecs/wm8731.c
index 5276062d6c79..10d492b6a5b4 100644
--- a/sound/soc/codecs/wm8731.c
+++ b/sound/soc/codecs/wm8731.c
@@ -407,10 +407,10 @@ static int wm8731_set_dai_fmt(struct snd_soc_dai *codec_dai,
 		iface |= 0x0001;
 		break;
 	case SND_SOC_DAIFMT_DSP_A:
-		iface |= 0x0003;
+		iface |= 0x0013;
 		break;
 	case SND_SOC_DAIFMT_DSP_B:
-		iface |= 0x0013;
+		iface |= 0x0003;
 		break;
 	default:
 		return -EINVAL;
diff --git a/sound/soc/codecs/wm8990.c b/sound/soc/codecs/wm8990.c
index 837978e16e9d..ded9ed854a1f 100644
--- a/sound/soc/codecs/wm8990.c
+++ b/sound/soc/codecs/wm8990.c
@@ -1264,6 +1264,8 @@ static int wm8990_set_bias_level(struct snd_soc_codec *codec,
 
 		/* disable POBCTRL, SOFT_ST and BUFDCOPEN */
 		snd_soc_write(codec, WM8990_ANTIPOP2, 0x0);
+
+		codec->cache_sync = 1;
 		break;
 	}